diff --git a/reinforcement_learning.py b/reinforcement_learning.py
new file mode 100644
index 0000000000000000000000000000000000000000..b2ff13390f24d3a1a3a6abb2155cbf37a9ec6747
--- /dev/null
+++ b/reinforcement_learning.py
@@ -0,0 +1,14 @@
+from IPython.display import clear_output
+import time
+
+def animate(frames, delay_per_frame):
+    for i, frame in enumerate(frames):
+        clear_output(wait=True)
+        print(frame['frame'])
+        print(f"Episode: {frame['episode']}")
+        print(f"Timestep: {i + 1} / {len(frames)}")
+        print(f"State: {frame['state']}")
+        print(f"Action: {frame['action']}")
+        print(f"Reward: {frame['reward']}")
+        print(f"Penalties: {frame['penalties']}")
+        time.sleep(delay_per_frame)
diff --git a/requirements.txt b/requirements.txt
index 845231f285d643ed0697de8bdc84caabf16ae374..223cc1c10ce8beaaf4d8f513332522284e97bef1 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -10,3 +10,6 @@ scipy==1.7.0
 python-constraint==1.4.0
 unified-planning==0.6.0
 up-pyperplan==1.0.0
+
+gym==0.18.3
+ipython