diff --git a/configs/config.py b/configs/config.py
index 030c9c72efe43e552bb1f2267de972a4a2300ec4..5a258fc6ef6576be3cb2461a0a50966852d3c912 100644
--- a/configs/config.py
+++ b/configs/config.py
@@ -302,7 +302,7 @@ def get_config():
     parser.add_argument("--log_interval", type=int, 
                         default=1, help="time duration between contiunous twice log printing.")
     parser.add_argument("--model_dir", type=str, 
-                        default='./trained_models/8800_six_nights/run1/models', help="by default None. set the path to pretrained model.")
+                        default='./trained_models/7010_after_christmas/run1/models', help="by default None. set the path to pretrained model.")
 
     # eval parameters
     parser.add_argument("--use_eval", action='store_true', 
diff --git a/scalarized_reward_wrapper.py b/scalarized_reward_wrapper.py
index 3b982ab74236e50523fe0b37fdc16cd75ba3488e..035ec5edb0949409fc98428fa80cadcf93962179 100644
--- a/scalarized_reward_wrapper.py
+++ b/scalarized_reward_wrapper.py
@@ -55,15 +55,15 @@ class ScalarizedRewardWrapper(gym.RewardWrapper):
                       - 0.5*reward[agent_id]['enemy_time_step_radars_detected']
             for agent_id in reward
         })
-        agent_id = 'g0'
-        print("position_error: ", 0.001*reward[agent_id]['position_error'])
-        print("enemy_position_error: ", -0.001*reward[agent_id]['enemy_position_error'])
-        #print("aircraft_share_detected: ", reward[agent_id]['aircraft_share_detected'])
-        print("share_radar_actions: ", 0.5*reward[agent_id]['share_radar_actions'])
-        #print("enemy_radar_share_detected: ", -reward[agent_id]['enemy_radar_share_detected'])
-        print("time_step_aircrafts_detected: ", reward[agent_id]['time_step_aircrafts_detected'])
-        print("enemy_time_step_radars_detected: ", -0.5*reward[agent_id]['enemy_time_step_radars_detected'])
-        print()
+        # agent_id = 'g0'
+        # print("position_error: ", 0.001*reward[agent_id]['position_error'])
+        # print("enemy_position_error: ", -0.001*reward[agent_id]['enemy_position_error'])
+        # print("aircraft_share_detected: ", reward[agent_id]['aircraft_share_detected'])
+        # print("share_radar_actions: ", 0.5*reward[agent_id]['share_radar_actions'])
+        # print("enemy_radar_share_detected: ", -reward[agent_id]['enemy_radar_share_detected'])
+        # print("time_step_aircrafts_detected: ", reward[agent_id]['time_step_aircrafts_detected'])
+        # print("enemy_time_step_radars_detected: ", -0.5*reward[agent_id]['enemy_time_step_radars_detected'])
+        # print()
 
        # if self.eval_==True:
         # new_reward = dict({
diff --git a/trained_models/7010_after_christmas/config.py b/trained_models/7010_after_christmas/config.py
new file mode 100644
index 0000000000000000000000000000000000000000..49a56d956f19453b26a58c0aa0776bb0f8238615
--- /dev/null
+++ b/trained_models/7010_after_christmas/config.py
@@ -0,0 +1,331 @@
+import argparse
+from behaviour import behaviour_choices
+
+def get_config():
+    """
+    The configuration parser for common hyperparameters of all environment. 
+    Please reach each `scripts/train/<env>_runner.py` file to find private hyperparameters
+    only used in <env>.
+
+    Prepare parameters:
+        --algorithm_name <algorithm_name>
+            specifiy the algorithm, including `["happo", "hatrpo"]`
+        --experiment_name <str>
+            an identifier to distinguish different experiment.
+        --seed <int>
+            set seed for numpy and torch 
+        --seed_specify
+            by default True Random or specify seed for numpy/torch
+        --runing_id <int>
+            the runing index of experiment (default=1)
+        --cuda
+            by default True, will use GPU to train; or else will use CPU; 
+        --cuda_deterministic
+            by default, make sure random seed effective. if set, bypass such function.
+        --n_training_threads <int>
+            number of training threads working in parallel. by default 1
+        --n_rollout_threads <int>
+            number of parallel envs for training rollout. by default 32
+        --n_eval_rollout_threads <int>
+            number of parallel envs for evaluating rollout. by default 1
+        --n_render_rollout_threads <int>
+            number of parallel envs for rendering, could only be set as 1 for some environments.
+        --num_env_steps <int>
+            number of env steps to train (default: 10e6)
+
+    
+    Env parameters:
+        --env_name <str>
+            specify the name of environment
+        --use_obs_instead_of_state
+            [only for some env] by default False, will use global state; or else will use concatenated local obs.
+    
+    Replay Buffer parameters:
+        --episode_length <int>
+            the max length of episode in the buffer. 
+    
+    Network parameters:
+        --share_policy
+            by default True, all agents will share the same network; set to make training agents use different policies. 
+        --use_centralized_V
+            by default True, use centralized training mode; or else will decentralized training mode.
+        --stacked_frames <int>
+            Number of input frames which should be stack together.
+        --hidden_size <int>
+            Dimension of hidden layers for actor/critic networks
+        --layer_N <int>
+            Number of layers for actor/critic networks
+        --use_ReLU
+            by default True, will use ReLU. or else will use Tanh.
+        --use_popart
+            by default True, use running mean and std to normalize rewards. 
+        --use_feature_normalization
+            by default True, apply layernorm to normalize inputs. 
+        --use_orthogonal
+            by default True, use Orthogonal initialization for weights and 0 initialization for biases. or else, will use xavier uniform inilialization.
+        --gain
+            by default 0.01, use the gain # of last action layer
+        --use_naive_recurrent_policy
+            by default False, use the whole trajectory to calculate hidden states.
+        --use_recurrent_policy
+            by default, use Recurrent Policy. If set, do not use.
+        --recurrent_N <int>
+            The number of recurrent layers ( default 1).
+        --data_chunk_length <int>
+            Time length of chunks used to train a recurrent_policy, default 10.
+    
+    Optimizer parameters:
+        --lr <float>
+            learning rate parameter,  (default: 5e-4, fixed).
+        --critic_lr <float>
+            learning rate of critic  (default: 5e-4, fixed)
+        --opti_eps <float>
+            RMSprop optimizer epsilon (default: 1e-5)
+        --weight_decay <float>
+            coefficience of weight decay (default: 0)
+    
+    TRPO parameters:
+        --kl_threshold <float>
+            the threshold of kl-divergence (default: 0.01)
+        --ls_step <int> 
+            the step of line search (default: 10)
+        --accept_ratio <float>
+            accept ratio of loss improve (default: 0.5)
+    
+    PPO parameters:
+        --ppo_epoch <int>
+            number of ppo epochs (default: 15)
+        --use_clipped_value_loss 
+            by default, clip loss value. If set, do not clip loss value.
+        --clip_param <float>
+            ppo clip parameter (default: 0.2)
+        --num_mini_batch <int>
+            number of batches for ppo (default: 1)
+        --entropy_coef <float>
+            entropy term coefficient (default: 0.01)
+        --use_max_grad_norm 
+            by default, use max norm of gradients. If set, do not use.
+        --max_grad_norm <float>
+            max norm of gradients (default: 0.5)
+        --use_gae
+            by default, use generalized advantage estimation. If set, do not use gae.
+        --gamma <float>
+            discount factor for rewards (default: 0.99)
+        --gae_lambda <float>
+            gae lambda parameter (default: 0.95)
+        --use_proper_time_limits
+            by default, the return value does consider limits of time. If set, compute returns with considering time limits factor.
+        --use_huber_loss
+            by default, use huber loss. If set, do not use huber loss.
+        --use_value_active_masks
+            by default True, whether to mask useless data in value loss.  
+        --huber_delta <float>
+            coefficient of huber loss.  
+
+    
+    Run parameters：
+        --use_linear_lr_decay
+            by default, do not apply linear decay to learning rate. If set, use a linear schedule on the learning rate
+        --save_interval <int>
+            time duration between contiunous twice models saving.
+        --log_interval <int>
+            time duration between contiunous twice log printing.
+        --model_dir <str>
+            by default None. set the path to pretrained model.
+
+    Eval parameters:
+        --use_eval
+            by default, do not start evaluation. If set`, start evaluation alongside with training.
+        --eval_interval <int>
+            time duration between contiunous twice evaluation progress.
+        --eval_episodes <int>
+            number of episodes of a single evaluation.
+    
+    Render parameters:
+        --save_gifs
+            by default, do not save render video. If set, save video.
+        --use_render
+            by default, do not render the env during training. If set, start render. Note: something, the environment has internal render process which is not controlled by this hyperparam.
+        --render_episodes <int>
+            the number of episodes to render a given env
+        --ifi <float>
+            the play interval of each rendered image in saved video.
+    
+    Pretrained parameters:
+        
+    """
+    parser = argparse.ArgumentParser(description='onpolicy_algorithm', formatter_class=argparse.RawDescriptionHelpFormatter)
+
+    # prepare parameters
+    parser.add_argument("--algorithm_name", type=str,
+                        default='happo', choices=["happo","hatrpo"])
+    parser.add_argument("--experiment_name", type=str, 
+                        default="check", help="an identifier to distinguish different experiment.")
+    parser.add_argument("--seed", type=int, 
+                        default=1, help="Random seed for numpy/torch")
+    parser.add_argument("--seed_specify", action="store_true",
+                        default=False, help="Random or specify seed for numpy/torch")
+    parser.add_argument("--red_behaviour", choices=behaviour_choices, type=str.lower,
+                        default="simpleone", help="name of red behaviour to use for training. Ignored if rand_red_behaviour is True.")
+    parser.add_argument("--rand_red_behaviour", type=bool,
+                        default=True, help="Randomizes opponent behaviour in each simulation for training. Uses red_behaviour if False.")
+    parser.add_argument("--rand_size", type=bool,
+                        default=True, help="Randomizes both teams, teamsize in each simulation for training.")
+    parser.add_argument("--red_size", type=int,
+                        default=2, help="2<=Size of red team<=7, works only with rand_size==false")
+    parser.add_argument("--green_size", type=int,
+                        default=2, help="2<=Size of green team<=7, works only with rand_size==false")
+    parser.add_argument("--runing_id", type=int, 
+                        default=1, help="the runing index of experiment")
+    parser.add_argument("--cuda", action='store_false', 
+                        default=True, help="by default True, will use GPU to train; or else will use CPU;")
+    parser.add_argument("--cuda_deterministic", action='store_false', 
+                        default=False, help="by default, make sure random seed effective. if set, bypass such function.")
+    parser.add_argument("--n_training_threads", type=int,
+                        default=1, help="Number of torch threads for training")
+    parser.add_argument("--n_rollout_threads", type=int, 
+                        default=20, help="Number of parallel envs for training rollouts")
+    parser.add_argument("--n_eval_rollout_threads", type=int, 
+                        default=1, help="Number of parallel envs for evaluating rollouts")
+    parser.add_argument("--n_render_rollout_threads", type=int, 
+                        default=1, help="Number of parallel envs for rendering rollouts")
+    parser.add_argument("--num_env_steps", type=int, 
+                        default=600*10*10000, help='Number of environment steps to train (default: 6000)') #600 ts x 20 rollout threads x 10 episode count
+                        #time = 600*20*1000 / fps (250)
+    parser.add_argument("--user_name", type=str, 
+                        default='marl',help="[for wandb usage], to specify user's name for simply collecting training data.")
+    # env parameters
+    parser.add_argument("--env_name", type=str, 
+                        default='scontrol', help="specify the name of environment")
+    parser.add_argument("--use_obs_instead_of_state", action='store_true',
+                        default=False, help="Whether to use global state or concatenated obs")
+
+    # replay buffer parameters
+    parser.add_argument("--episode_length", type=int,
+                        default=600, help="Max length for any episode")
+
+    # network parameters
+    parser.add_argument("--share_policy", action='store_false',
+                        default=True, help='Whether agent share the same policy')
+    parser.add_argument("--use_centralized_V", action='store_false',
+                        default=True, help="Whether to use centralized V function")
+    parser.add_argument("--stacked_frames", type=int, 
+                        default=100, help="Dimension of hidden layers for actor/critic networks")
+    parser.add_argument("--use_stacked_frames", action='store_true',
+                        default=True, help="Whether to use stacked_frames")
+    parser.add_argument("--hidden_size", type=int, 
+                        default=64, help="Dimension of hidden layers for actor/critic networks") 
+    parser.add_argument("--layer_N", type=int, 
+                        default=2, help="Number of layers for actor/critic networks")
+    parser.add_argument("--use_ReLU", action='store_false',
+                        default=True, help="Whether to use ReLU")
+    parser.add_argument("--use_popart", action='store_false', 
+                        default=False, help="by default True, use running mean and std to normalize rewards.")
+    parser.add_argument("--use_valuenorm", action='store_false', 
+                        default=False, help="by default True, use running mean and std to normalize rewards.")
+    parser.add_argument("--use_feature_normalization", action='store_false',
+                        default=True, help="Whether to apply layernorm to the inputs")
+    parser.add_argument("--use_orthogonal", action='store_false', 
+                        default=True, help="Whether to use Orthogonal initialization for weights and 0 initialization for biases")
+    parser.add_argument("--gain", type=float, 
+                        default=0.01, help="The gain # of last action layer")
+
+    # recurrent parameters
+    parser.add_argument("--use_naive_recurrent_policy", action='store_true',
+                        default=False, help='Whether to use a naive recurrent policy')
+    parser.add_argument("--use_recurrent_policy", action='store_true',
+                        default=False, help='use a recurrent policy')
+    parser.add_argument("--recurrent_N", type=int, 
+                        default=1, help="The number of recurrent layers.")
+    parser.add_argument("--data_chunk_length", type=int, 
+                        default=10, help="Time length of chunks used to train a recurrent_policy")
+    
+    # optimizer parameters
+    parser.add_argument("--lr", type=float, 
+                        default=5e-4, help='learning rate (default: 5e-4)')
+    parser.add_argument("--critic_lr", type=float, 
+                        default=5e-4, help='critic learning rate (default: 5e-4)')
+    parser.add_argument("--opti_eps", type=float, 
+                        default=1e-5, help='RMSprop optimizer epsilon (default: 1e-5)')
+    parser.add_argument("--weight_decay", type=float, default=0)
+    parser.add_argument("--std_x_coef", type=float, default=1)
+    parser.add_argument("--std_y_coef", type=float, default=0.5)
+
+
+    # trpo parameters
+    parser.add_argument("--kl_threshold", type=float, 
+                        default=0.01, help='the threshold of kl-divergence (default: 0.01)')
+    parser.add_argument("--ls_step", type=int, 
+                        default=10, help='number of line search (default: 10)')
+    parser.add_argument("--accept_ratio", type=float, 
+                        default=0.5, help='accept ratio of loss improve (default: 0.5)')
+
+    # ppo parameters
+    parser.add_argument("--ppo_epoch", type=int, 
+                        default=10, help='number of ppo epochs (default: 15)')
+    parser.add_argument("--use_clipped_value_loss", action='store_false', 
+                        default=False, help="by default, clip loss value. If set, do not clip loss value.")
+    parser.add_argument("--clip_param", type=float, 
+                        default=0.2, help='ppo clip parameter (default: 0.2)')
+    parser.add_argument("--num_mini_batch", type=int, 
+                        default=1, help='number of batches for ppo (default: 1)')
+    parser.add_argument("--entropy_coef", type=float, 
+                        default=0.01, help='entropy term coefficient (default: 0.01)')
+    parser.add_argument("--value_loss_coef", type=float,
+                        default=0.01, help='value loss coefficient (default: 0.5)')
+    parser.add_argument("--use_max_grad_norm", action='store_false', 
+                        default=True, help="by default, use max norm of gradients. If set, do not use.")
+    parser.add_argument("--max_grad_norm", type=float, 
+                        default=0.5, help='max norm of gradients (default: 0.5)')
+    parser.add_argument("--use_gae", action='store_false',
+                        default=True, help='use generalized advantage estimation')
+    parser.add_argument("--gamma", type=float, default=0.99,
+                        help='discount factor for rewards (default: 0.99)')
+    parser.add_argument("--gae_lambda", type=float, default=0.95,
+                        help='gae lambda parameter (default: 0.95)')
+    parser.add_argument("--use_proper_time_limits", action='store_true',
+                        default=True, help='compute returns taking into account time limits')
+    parser.add_argument("--use_huber_loss", action='store_false', 
+                        default=True, help="by default, use huber loss. If set, do not use huber loss.")
+    parser.add_argument("--use_value_active_masks", action='store_false', 
+                        default=True, help="by default True, whether to mask useless data in value loss.")
+    parser.add_argument("--use_policy_active_masks", action='store_false', 
+                        default=True, help="by default True, whether to mask useless data in policy loss.")
+    parser.add_argument("--huber_delta", type=float, 
+                        default=10.0, help=" coefficience of huber loss.")
+
+    # run parameters
+    parser.add_argument("--use_linear_lr_decay", action='store_true',
+                        default=False, help='use a linear schedule on the learning rate')
+    parser.add_argument("--save_interval", type=int, 
+                        default=10, help="time duration between contiunous twice models saving.")
+    parser.add_argument("--log_interval", type=int, 
+                        default=1, help="time duration between contiunous twice log printing.")
+    parser.add_argument("--model_dir", type=str, 
+                        default='./trained_models/9191_fournights/run1/models', help="by default None. set the path to pretrained model.")
+
+    # eval parameters
+    parser.add_argument("--use_eval", action='store_true', 
+                        default=True, help="by default, do not start evaluation. If set`, start evaluation alongside with training.")
+    parser.add_argument("--eval_interval", type=int, 
+                        default=10, help="time duration between contiunous twice evaluation progress.")
+    parser.add_argument("--eval_episodes", type=int, 
+                        default=2, help="number of episodes of a single evaluation.")
+    parser.add_argument("--eval_render", type=bool,
+                        default=False, help="visualizes the model every eval. works on top of the 'eval' setting in multiagent_rl_train.")
+    parser.add_argument("--visualise_delay", type=int,
+                        default=1, help="numer of milliseconds to wait between steps when drawing eval render.")
+    parser.add_argument("--only_delay_middle", type=bool,
+                        default=True, help="uses 0 delay for time < 150 and time > 350, and visualise delay for the middle")
+
+    # render parameters
+    parser.add_argument("--save_gifs", action='store_true', 
+                        default=False, help="by default, do not save render video. If set, save video.")
+    parser.add_argument("--use_render", action='store_true', 
+                        default=False, help="by default, do not render the env during training. If set, start render. Note: something, the environment has internal render process which is not controlled by this hyperparam.")
+    parser.add_argument("--render_episodes", type=int, 
+                        default=5, help="the number of episodes to render a given env")
+    parser.add_argument("--ifi", type=float, 
+                        default=0.1, help="the play interval of each rendered image in saved video.")
+
+    return parser
\ No newline at end of file
diff --git a/trained_models/7010_after_christmas/reward b/trained_models/7010_after_christmas/reward
new file mode 100644
index 0000000000000000000000000000000000000000..e9752e127f4b79df6c7dbbc11e875b1197f7fcf9
--- /dev/null
+++ b/trained_models/7010_after_christmas/reward
@@ -0,0 +1,5 @@
+ agent_id: + (0.001*reward[agent_id]['position_error'] - 0.001*reward[agent_id]['enemy_position_error'])
+                      + 0.5*reward[agent_id]['share_radar_actions']
+                      + reward[agent_id]['time_step_aircrafts_detected']
+                      - 0.5*reward[agent_id]['enemy_time_step_radars_detected']
+eval: samma
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/actor_grad_norm/agent0/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/actor_grad_norm/agent0/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..72d500a5357d405487121f528f7c102a674fd394
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/actor_grad_norm/agent0/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/average_step_adversarial_rewards/agent0/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_adversarial_rewards/agent0/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..dffb9f6911c621124e66232362e6d81b2af014a7
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_adversarial_rewards/agent0/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/average_step_external_rewards/agent0/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_external_rewards/agent0/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d78095cdf9a0d4db1e6727dfa8802cfc11a096d7
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_external_rewards/agent0/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/average_step_rewards/agent0/average_step_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_rewards/agent0/average_step_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d9596eca26050315f21b737f85b37ec6e5759356
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_rewards/agent0/average_step_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/average_step_rnd_rewards/agent0/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_rnd_rewards/agent0/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..8cf90b9088d93de1a9dd7d5447cd04c5673da86c
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/average_step_rnd_rewards/agent0/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/critic_grad_norm/agent0/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/critic_grad_norm/agent0/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..3b9eb05deb68b6cb786d62a014aa00d5ca1bb2ef
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/critic_grad_norm/agent0/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/dist_entropy/agent0/dist_entropy/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/dist_entropy/agent0/dist_entropy/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..ecb268ba3f593318316f917fd50c47738cc3c9df
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/dist_entropy/agent0/dist_entropy/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/generator_actor_grad_norm/agent0/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/generator_actor_grad_norm/agent0/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..a721b906bad32ad6446744b93004d5e7db5336d5
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/generator_actor_grad_norm/agent0/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/generator_actor_loss/agent0/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/generator_actor_loss/agent0/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..2b04c4b306f08ba022f976e8e7b2eab015a6e2de
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/generator_actor_loss/agent0/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/generator_critic_grad_norm/agent0/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/generator_critic_grad_norm/agent0/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..6d817d12259dc7bf586e1fedf36594a96e9df209
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/generator_critic_grad_norm/agent0/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/generator_value_loss/agent0/generator_value_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/generator_value_loss/agent0/generator_value_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..c5aad44f5528563e2ec919731ecc92621b84a43b
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/generator_value_loss/agent0/generator_value_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/policy_loss/agent0/policy_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/policy_loss/agent0/policy_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..c116e38ab61be386413c55675e0a1590799e3a1d
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/policy_loss/agent0/policy_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/ratio/agent0/ratio/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/ratio/agent0/ratio/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..02c63711965e74fb48726bdce6bc414e457e9565
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/ratio/agent0/ratio/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/rnd_grad_norm/agent0/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/rnd_grad_norm/agent0/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..1c85fa5a044fbeb5bfc7d0348f28e5f347673ff4
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/rnd_grad_norm/agent0/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/rnd_loss/agent0/rnd_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/rnd_loss/agent0/rnd_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..a09c7f456cddd8ea9476df70f5642f5c24cd5724
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/rnd_loss/agent0/rnd_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent0/value_loss/agent0/value_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent0/value_loss/agent0/value_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d58c1bc9e61a94acd58b850bf44d385844d7f935
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent0/value_loss/agent0/value_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/actor_grad_norm/agent1/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/actor_grad_norm/agent1/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..6b2b137975aba00717e4ffaf61252a0fd9631c03
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/actor_grad_norm/agent1/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/average_step_adversarial_rewards/agent1/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_adversarial_rewards/agent1/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..17022596e80ebac2c31601b3ec5c8b042600fb08
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_adversarial_rewards/agent1/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/average_step_external_rewards/agent1/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_external_rewards/agent1/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..34ec700014a2af0e922ad2c874098c52b6461937
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_external_rewards/agent1/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/average_step_rewards/agent1/average_step_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_rewards/agent1/average_step_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..b32576641c1653b4db909d6ea0c59effe679f446
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_rewards/agent1/average_step_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/average_step_rnd_rewards/agent1/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_rnd_rewards/agent1/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..da4cd92787e3b001c2b54d9c86b4b33b88db354b
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/average_step_rnd_rewards/agent1/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/critic_grad_norm/agent1/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/critic_grad_norm/agent1/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..ded7e59a025785a478ef3630b4a2d9b152f0f166
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/critic_grad_norm/agent1/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/dist_entropy/agent1/dist_entropy/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/dist_entropy/agent1/dist_entropy/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..65789741fff9de7c81670b736db1e77a2536bc75
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/dist_entropy/agent1/dist_entropy/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/generator_actor_grad_norm/agent1/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/generator_actor_grad_norm/agent1/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..0389043fc25f3958614bf48c43a9c519e07a321e
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/generator_actor_grad_norm/agent1/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/generator_actor_loss/agent1/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/generator_actor_loss/agent1/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..80b3ff7216ced8cc25d8103805990ab01e2a90c6
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/generator_actor_loss/agent1/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/generator_critic_grad_norm/agent1/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/generator_critic_grad_norm/agent1/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..e5fa52237da5810f6fcec1ef3a3a3bbb1524c382
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/generator_critic_grad_norm/agent1/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/generator_value_loss/agent1/generator_value_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/generator_value_loss/agent1/generator_value_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..19a14601c0dbe9e917e2d9f9aab54a49f3e30b12
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/generator_value_loss/agent1/generator_value_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/policy_loss/agent1/policy_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/policy_loss/agent1/policy_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..67c340a5ef658694f16b58be0787c7fb66195b86
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/policy_loss/agent1/policy_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/ratio/agent1/ratio/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/ratio/agent1/ratio/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..2042623dc042dd877290e07e1c9045921d42283a
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/ratio/agent1/ratio/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/rnd_grad_norm/agent1/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/rnd_grad_norm/agent1/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..eb9fe956d5c1371fe7d575149d2c0b72cf07e011
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/rnd_grad_norm/agent1/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/rnd_loss/agent1/rnd_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/rnd_loss/agent1/rnd_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d4417d1202b5399c3e0c5796df8e033844312626
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/rnd_loss/agent1/rnd_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent1/value_loss/agent1/value_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent1/value_loss/agent1/value_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..ec5add16d0e221c31d901bdff2ca7b6f3c3b820e
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent1/value_loss/agent1/value_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/actor_grad_norm/agent2/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/actor_grad_norm/agent2/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..ce5ca92cdeb3d72abd3e9944fd02f4b6bbdfbe63
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/actor_grad_norm/agent2/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/average_step_adversarial_rewards/agent2/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_adversarial_rewards/agent2/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..e68f3672fd2f7e3f3553cb47340c83d295765409
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_adversarial_rewards/agent2/average_step_adversarial_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/average_step_external_rewards/agent2/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_external_rewards/agent2/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..79cccd5c67551a3eb53587e369ef261ec40dc8cc
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_external_rewards/agent2/average_step_external_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/average_step_rewards/agent2/average_step_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_rewards/agent2/average_step_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..9e006a15fd906d7095b18b8a280c9088f69f5297
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_rewards/agent2/average_step_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/average_step_rnd_rewards/agent2/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_rnd_rewards/agent2/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..867cce9b316b8baafef6f7d1cdd21f47faf80e27
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/average_step_rnd_rewards/agent2/average_step_rnd_rewards/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/critic_grad_norm/agent2/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/critic_grad_norm/agent2/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..7e669e5a06b6fb05107ca990701d7fa1b3220cdb
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/critic_grad_norm/agent2/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/dist_entropy/agent2/dist_entropy/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/dist_entropy/agent2/dist_entropy/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..b9d770526b5a8f30c39bdc8e91a788b3c8098b8e
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/dist_entropy/agent2/dist_entropy/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/generator_actor_grad_norm/agent2/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/generator_actor_grad_norm/agent2/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..3440fc730c53890dfb684de67e1bc81ff2a75bef
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/generator_actor_grad_norm/agent2/generator_actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/generator_actor_loss/agent2/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/generator_actor_loss/agent2/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..c79fc432d6501c65adce784ab63d318d847881ef
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/generator_actor_loss/agent2/generator_actor_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/generator_critic_grad_norm/agent2/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/generator_critic_grad_norm/agent2/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..a3b59acc526cc4125a44aae4955d810b0d170a51
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/generator_critic_grad_norm/agent2/generator_critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/generator_value_loss/agent2/generator_value_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/generator_value_loss/agent2/generator_value_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..a3ed1830e50faf2652d04e54497c691e919e97c3
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/generator_value_loss/agent2/generator_value_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/policy_loss/agent2/policy_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/policy_loss/agent2/policy_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..40ad32f510e36836b125a38b0c87d53f3c13e656
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/policy_loss/agent2/policy_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/ratio/agent2/ratio/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/ratio/agent2/ratio/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..55e8e5aed8d7bf891b69c7668679649beccb75e9
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/ratio/agent2/ratio/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/rnd_grad_norm/agent2/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/rnd_grad_norm/agent2/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..132cce2176b2e1a569691edc621549fd8eb9640e
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/rnd_grad_norm/agent2/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/rnd_loss/agent2/rnd_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/rnd_loss/agent2/rnd_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..b12c017a75a0dc635f118e6d6d878e293f0bda01
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/rnd_loss/agent2/rnd_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent2/value_loss/agent2/value_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent2/value_loss/agent2/value_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..55fd21368f411f67d334de003d9284cbd9ada274
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent2/value_loss/agent2/value_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/actor_grad_norm/agent3/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/actor_grad_norm/agent3/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..60e72e19451075413132c3c34ea622d9c8a410ec
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/actor_grad_norm/agent3/actor_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/average_step_adversarial_rewards/agent3/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_adversarial_rewards/agent3/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..b7c32c8c731ee8561777144be1baed9dca1b6d0e
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_adversarial_rewards/agent3/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/average_step_external_rewards/agent3/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_external_rewards/agent3/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..1b68dbb07910f81cb3d835b39b699217213e1fd1
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_external_rewards/agent3/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/average_step_rewards/agent3/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_rewards/agent3/average_step_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..b58f3ffd7f9d15a231f37e2e78b18ed90f66b34f
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_rewards/agent3/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/average_step_rnd_rewards/agent3/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_rnd_rewards/agent3/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d53191301d0bf8d3d164e85789ce9703d1908248
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/average_step_rnd_rewards/agent3/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/critic_grad_norm/agent3/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/critic_grad_norm/agent3/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..40de15a395051e978a625940b85c199452d0b0cc
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/critic_grad_norm/agent3/critic_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/dist_entropy/agent3/dist_entropy/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/dist_entropy/agent3/dist_entropy/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..322309b7f240f3a3464b2f97536334f2adf0ec0a
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/dist_entropy/agent3/dist_entropy/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/generator_actor_grad_norm/agent3/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/generator_actor_grad_norm/agent3/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..fda05139dafc137eddfe7156407cd632726a20c0
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/generator_actor_grad_norm/agent3/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/generator_actor_loss/agent3/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/generator_actor_loss/agent3/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..6d3dad2e7bdb707a5112712816cdc220b0ae4b0e
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/generator_actor_loss/agent3/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/generator_critic_grad_norm/agent3/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/generator_critic_grad_norm/agent3/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..ccccc64f68ed45b0d7efdee313a235fbf8ff6865
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/generator_critic_grad_norm/agent3/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/generator_value_loss/agent3/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/generator_value_loss/agent3/generator_value_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..242bb46c60fb9d4abbec042e99446eb33100ce87
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/generator_value_loss/agent3/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/policy_loss/agent3/policy_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/policy_loss/agent3/policy_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..f01ac2fe70c8a09f7957b420bce3c4b17bb61905
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/policy_loss/agent3/policy_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/ratio/agent3/ratio/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/ratio/agent3/ratio/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..abc5458b73295dcc93bda4fa7bde2a97aca51fdd
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/ratio/agent3/ratio/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/rnd_grad_norm/agent3/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/rnd_grad_norm/agent3/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..fe8a1d0c865671a9303484843522f5c994d3fb25
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/rnd_grad_norm/agent3/rnd_grad_norm/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/rnd_loss/agent3/rnd_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/rnd_loss/agent3/rnd_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..cd9e9f02fc3844aa3c19acbd12750a1f4bb55b2d
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/rnd_loss/agent3/rnd_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent3/value_loss/agent3/value_loss/events.out.tfevents.1671187947.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent3/value_loss/agent3/value_loss/events.out.tfevents.1671187947.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d67ef2384701f93d08d7b95facdc7087c2bb7831
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent3/value_loss/agent3/value_loss/events.out.tfevents.1671187947.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/actor_grad_norm/agent4/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/actor_grad_norm/agent4/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d55b62e47032c0924bcb57239b3c0e9cecc246aa
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/actor_grad_norm/agent4/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/average_step_adversarial_rewards/agent4/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_adversarial_rewards/agent4/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..458ab7d945f4802454b329745fc94e0f3e496afd
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_adversarial_rewards/agent4/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/average_step_external_rewards/agent4/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_external_rewards/agent4/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..ae4f15b34002f7e934de23e16c1686584991c00a
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_external_rewards/agent4/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/average_step_rewards/agent4/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_rewards/agent4/average_step_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..6330436f1f2c29ea9df1b770ec07976fa72da191
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_rewards/agent4/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/average_step_rnd_rewards/agent4/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_rnd_rewards/agent4/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..7436f84df479b69f4897124f84308d0958e4f9d3
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/average_step_rnd_rewards/agent4/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/critic_grad_norm/agent4/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/critic_grad_norm/agent4/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..8dc1d96d0fc8ac8fab3a3d1f30011ef896a487b1
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/critic_grad_norm/agent4/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/dist_entropy/agent4/dist_entropy/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/dist_entropy/agent4/dist_entropy/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..28be9eb4553067b42093cea9a5209487afc40740
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/dist_entropy/agent4/dist_entropy/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/generator_actor_grad_norm/agent4/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/generator_actor_grad_norm/agent4/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..eff6917cb1fb608ebbc8aa18ef26cf30c33ff2d6
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/generator_actor_grad_norm/agent4/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/generator_actor_loss/agent4/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/generator_actor_loss/agent4/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..013228d19e2bbd98ab83402bac6070dad4c43c90
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/generator_actor_loss/agent4/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/generator_critic_grad_norm/agent4/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/generator_critic_grad_norm/agent4/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..0551c2adc34d1882d92ba8d7aeb63777e0666c60
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/generator_critic_grad_norm/agent4/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/generator_value_loss/agent4/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/generator_value_loss/agent4/generator_value_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..f51dd28d02dd2563b245cef3ddc11615ff0e6fec
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/generator_value_loss/agent4/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/policy_loss/agent4/policy_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/policy_loss/agent4/policy_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..fe36d9cc3a9ff2ba599acaff5ab72d95790e533c
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/policy_loss/agent4/policy_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/ratio/agent4/ratio/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/ratio/agent4/ratio/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..881596008954c3635960a9b626eed47751b45850
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/ratio/agent4/ratio/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/rnd_grad_norm/agent4/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/rnd_grad_norm/agent4/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..5a9b940821242550e1716bbe111f623a2af62b21
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/rnd_grad_norm/agent4/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/rnd_loss/agent4/rnd_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/rnd_loss/agent4/rnd_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..31c50f5ab534bcbc5d018f5aa1a0e767dbb418aa
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/rnd_loss/agent4/rnd_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent4/value_loss/agent4/value_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent4/value_loss/agent4/value_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..f40666fd3f087f7645f692dcb32c8bf630631853
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent4/value_loss/agent4/value_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/actor_grad_norm/agent5/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/actor_grad_norm/agent5/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..82630aa54eb9b4170b7eee0b3c08679b5fe3c076
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/actor_grad_norm/agent5/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/average_step_adversarial_rewards/agent5/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_adversarial_rewards/agent5/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..89cd748443e8fa4f900fc474e79a861a1e3f9874
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_adversarial_rewards/agent5/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/average_step_external_rewards/agent5/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_external_rewards/agent5/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..7e981d0bcb0adc61aa9d55df9d4decdcf0526bba
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_external_rewards/agent5/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/average_step_rewards/agent5/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_rewards/agent5/average_step_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..a8db48a4d69abaefe6d61196e18579ae7dbfa700
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_rewards/agent5/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/average_step_rnd_rewards/agent5/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_rnd_rewards/agent5/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..bff700f6192205249e5d3e14340f181a673dae55
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/average_step_rnd_rewards/agent5/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/critic_grad_norm/agent5/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/critic_grad_norm/agent5/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..3bcf89a421e47536e53fe73b449cde0af779fc12
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/critic_grad_norm/agent5/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/dist_entropy/agent5/dist_entropy/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/dist_entropy/agent5/dist_entropy/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..7f7de46ee3d41b4099b23f1c809078b31135eeff
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/dist_entropy/agent5/dist_entropy/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/generator_actor_grad_norm/agent5/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/generator_actor_grad_norm/agent5/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..116511ff4526926450969e8fcf71514cc52956a9
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/generator_actor_grad_norm/agent5/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/generator_actor_loss/agent5/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/generator_actor_loss/agent5/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..6a5691b5c32df132d53ca397ce7fd43c496df0f5
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/generator_actor_loss/agent5/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/generator_critic_grad_norm/agent5/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/generator_critic_grad_norm/agent5/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..e989d5136744b78956954e3e54b1ce842badfcfa
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/generator_critic_grad_norm/agent5/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/generator_value_loss/agent5/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/generator_value_loss/agent5/generator_value_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..2d7e70dc2c96f090ec9937690d5ca4c3ceda00e5
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/generator_value_loss/agent5/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/policy_loss/agent5/policy_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/policy_loss/agent5/policy_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..ab8735b4e91068c1249ef6351a065fa6869529fa
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/policy_loss/agent5/policy_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/ratio/agent5/ratio/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/ratio/agent5/ratio/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..af10265585e2b09094a758630be2e69b4e84cf31
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/ratio/agent5/ratio/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/rnd_grad_norm/agent5/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/rnd_grad_norm/agent5/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..a5a4c7d08edc8f805f134f07997a83329cf8692b
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/rnd_grad_norm/agent5/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/rnd_loss/agent5/rnd_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/rnd_loss/agent5/rnd_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..fc9d8b586d22360a096c83f354419c2317fbacbe
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/rnd_loss/agent5/rnd_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent5/value_loss/agent5/value_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent5/value_loss/agent5/value_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..99a9768192596508371b82d95655f9d954104e95
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent5/value_loss/agent5/value_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/actor_grad_norm/agent6/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/actor_grad_norm/agent6/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..d7d14844a55561d7ffa25e7b6e6bb0d2c522857d
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/actor_grad_norm/agent6/actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/average_step_adversarial_rewards/agent6/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_adversarial_rewards/agent6/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..24a9d121ec4e27a5cc8af51a3243c579273dbcaa
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_adversarial_rewards/agent6/average_step_adversarial_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/average_step_external_rewards/agent6/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_external_rewards/agent6/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..4873971d63db18dfffd987263403f77c10c0941b
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_external_rewards/agent6/average_step_external_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/average_step_rewards/agent6/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_rewards/agent6/average_step_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..3927b7b3e5e8830b7046adbc3b40b5ab42ab1ed7
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_rewards/agent6/average_step_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/average_step_rnd_rewards/agent6/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_rnd_rewards/agent6/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..01355a81619089a4ec3a6154939254a5adf2f1fe
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/average_step_rnd_rewards/agent6/average_step_rnd_rewards/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/critic_grad_norm/agent6/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/critic_grad_norm/agent6/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..7a9f471f85bb7a8246fa0449ea0e820bfc737986
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/critic_grad_norm/agent6/critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/dist_entropy/agent6/dist_entropy/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/dist_entropy/agent6/dist_entropy/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..f711cb73b9feac8522117a34fa627162f2669cac
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/dist_entropy/agent6/dist_entropy/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/generator_actor_grad_norm/agent6/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/generator_actor_grad_norm/agent6/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..e067be5fbcc118fb53debf5f8e3dcef0220045fa
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/generator_actor_grad_norm/agent6/generator_actor_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/generator_actor_loss/agent6/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/generator_actor_loss/agent6/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..eef78bd82fd46b15a92116b5d3accc18d8424592
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/generator_actor_loss/agent6/generator_actor_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/generator_critic_grad_norm/agent6/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/generator_critic_grad_norm/agent6/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..e3c5d2dddc53281bf778311e80496abe705676b1
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/generator_critic_grad_norm/agent6/generator_critic_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/generator_value_loss/agent6/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/generator_value_loss/agent6/generator_value_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..54a98797c88109d3253afe385762b27ff0d749b3
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/generator_value_loss/agent6/generator_value_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/policy_loss/agent6/policy_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/policy_loss/agent6/policy_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..fef770d3855afef239969fe0e19d4188fc112542
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/policy_loss/agent6/policy_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/ratio/agent6/ratio/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/ratio/agent6/ratio/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..e86836658a5e40c1ff15faeaa2033f021721052f
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/ratio/agent6/ratio/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/rnd_grad_norm/agent6/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/rnd_grad_norm/agent6/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..199f4c9a213363b1a6d2aa3df6f1cbeb849d33c0
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/rnd_grad_norm/agent6/rnd_grad_norm/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/rnd_loss/agent6/rnd_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/rnd_loss/agent6/rnd_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..97161020899f6b00c6ffb4023e44c05ce33d3791
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/rnd_loss/agent6/rnd_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/agent6/value_loss/agent6/value_loss/events.out.tfevents.1671187948.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/agent6/value_loss/agent6/value_loss/events.out.tfevents.1671187948.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..f897ef1ebcb866860d396b8561001e21c38e641d
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/agent6/value_loss/agent6/value_loss/events.out.tfevents.1671187948.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/eval_average_episode_rewards/eval_average_episode_rewards/events.out.tfevents.1671189724.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/eval_average_episode_rewards/eval_average_episode_rewards/events.out.tfevents.1671189724.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..7ce70d8df64c85d26f2db437aede9101d0dc4d0b
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/logs/eval_average_episode_rewards/eval_average_episode_rewards/events.out.tfevents.1671189724.maiex1-104 differ
diff --git a/trained_models/7010_after_christmas/run1/logs/events.out.tfevents.1671187744.maiex1-104 b/trained_models/7010_after_christmas/run1/logs/events.out.tfevents.1671187744.maiex1-104
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/trained_models/7010_after_christmas/run1/models/actor_agent0.pt b/trained_models/7010_after_christmas/run1/models/actor_agent0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ea3bf9c9f8ae006045ae78acd8efd6512fad2d75
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/actor_agent0.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/actor_agent1.pt b/trained_models/7010_after_christmas/run1/models/actor_agent1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cf59894a8c1740e2507b2c9e406a1d4084cae815
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/actor_agent1.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/actor_agent2.pt b/trained_models/7010_after_christmas/run1/models/actor_agent2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4bd4feff8941dcbb6a16c1c8e38e15f8a5144b8c
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/actor_agent2.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/actor_agent3.pt b/trained_models/7010_after_christmas/run1/models/actor_agent3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..43a67636f845706742f0966d7852a859d9dbe2ef
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/actor_agent3.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/actor_agent4.pt b/trained_models/7010_after_christmas/run1/models/actor_agent4.pt
new file mode 100644
index 0000000000000000000000000000000000000000..321799eead51cff8dcf1c141e62002a5d2210172
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/actor_agent4.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/actor_agent5.pt b/trained_models/7010_after_christmas/run1/models/actor_agent5.pt
new file mode 100644
index 0000000000000000000000000000000000000000..692e6fcf78ca085ec9db11a5dc663777c4f0a6c0
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/actor_agent5.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/actor_agent6.pt b/trained_models/7010_after_christmas/run1/models/actor_agent6.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dd0bb95b12edb398210f93c6f1831020c698d862
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/actor_agent6.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/critic_agent0.pt b/trained_models/7010_after_christmas/run1/models/critic_agent0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0b1669809b5d3126e5bb71760e3f332b6ec56873
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/critic_agent0.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/critic_agent1.pt b/trained_models/7010_after_christmas/run1/models/critic_agent1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de6c7bc7cccb1853655928855a9f8a922d77dd67
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/critic_agent1.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/critic_agent2.pt b/trained_models/7010_after_christmas/run1/models/critic_agent2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0384feed956e99c1d6bcb190fb48231568bee94e
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/critic_agent2.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/critic_agent3.pt b/trained_models/7010_after_christmas/run1/models/critic_agent3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4fe780b1dfcd9c04a9bdb0823834d1efbe8a64db
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/critic_agent3.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/critic_agent4.pt b/trained_models/7010_after_christmas/run1/models/critic_agent4.pt
new file mode 100644
index 0000000000000000000000000000000000000000..25d2f144b740940540a805495c323a4cac8ca0d3
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/critic_agent4.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/critic_agent5.pt b/trained_models/7010_after_christmas/run1/models/critic_agent5.pt
new file mode 100644
index 0000000000000000000000000000000000000000..57ed36d6e0feb645bf7d41a82ecbfa49567d6781
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/critic_agent5.pt differ
diff --git a/trained_models/7010_after_christmas/run1/models/critic_agent6.pt b/trained_models/7010_after_christmas/run1/models/critic_agent6.pt
new file mode 100644
index 0000000000000000000000000000000000000000..49fd3cd63463e3767b3411d63044d248128cb867
Binary files /dev/null and b/trained_models/7010_after_christmas/run1/models/critic_agent6.pt differ