gym

lightning_examples/reinforce-learning-DQN/.meta.yml

@@ -13,7 +13,7 @@ description: |
   2. Handle unsupervised learning by using an IterableDataset where the dataset itself is constantly updated during training
   3. Each training step carries has the agent taking an action in the environment and storing the experience in the IterableDataset
 requirements:
-  - gym
+  - gym <0.24
   - pygame
   - pandas
   - seaborn

lightning_examples/reinforce-learning-DQN/dqn.py

@@ -173,6 +173,10 @@ def play_step(
         action = self.get_action(net, epsilon, device)
 
         # do step in the environment
+        # So, in the deprecated version of gym, the env.step() has 4 values unpacked which is
+        #     obs, reward, done, info = env.step(action)
+        # In the latest version of gym, the step() function returns back an additional variable which is truncated.
+        #     obs, reward, terminated, truncated, info = env.step(action)
         new_state, reward, done, _ = self.env.step(action)
 
         exp = Experience(self.state, action, reward, done, new_state)