added model trained against random behaviours and random team size

configs/config.py

trained_models/9191_fournights/config.py

trained_models/9191_fournights/reward

...actor_grad_norm/events.out.tfevents.1670950489.maiex1-104

...rsarial_rewards/events.out.tfevents.1670950489.maiex1-104

...ge_step_rewards/events.out.tfevents.1670950489.maiex1-104

...ritic_grad_norm/events.out.tfevents.1670950489.maiex1-104

...t0/dist_entropy/events.out.tfevents.1670950489.maiex1-104

...nt0/policy_loss/events.out.tfevents.1670950489.maiex1-104

...io/agent0/ratio/events.out.tfevents.1670950489.maiex1-104

...ent0/value_loss/events.out.tfevents.1670950489.maiex1-104

...actor_grad_norm/events.out.tfevents.1670950489.maiex1-104

...rsarial_rewards/events.out.tfevents.1670950489.maiex1-104

...ge_step_rewards/events.out.tfevents.1670950489.maiex1-104

...ritic_grad_norm/events.out.tfevents.1670950489.maiex1-104

...t1/dist_entropy/events.out.tfevents.1670950489.maiex1-104

...nt1/policy_loss/events.out.tfevents.1670950489.maiex1-104

...io/agent1/ratio/events.out.tfevents.1670950489.maiex1-104

...ent1/value_loss/events.out.tfevents.1670950489.maiex1-104

...actor_grad_norm/events.out.tfevents.1670950489.maiex1-104