Update files

a2c_sb3_cartpole.py

+import numpy as np
+from tqdm import tqdm
+
 import gym
 from stable_baselines3 import A2C
 from stable_baselines3.common.env_util import make_vec_env
-from stable_baselines3.common.evaluation import evaluate_policy
 import matplotlib.pyplot as plt
-import numpy as np
-from tqdm import tqdm
+
 
 if __name__ == "__main__":
     episodes = 500
@@ -34,9 +35,6 @@ if __name__ == "__main__":
         
         episode_rewards.append(episode_reward)
 
-        # Log progress
-        # print(f"Episode: {episode + 1}, Reward: {episode_reward_sum}")
-
     # Save model
     model.save("a2c_cartpole_model")
 

reinforce_cartpole.py

@@ -31,7 +31,7 @@ if __name__ == "__main__":
     # Hyperparameters
     learning_rate = 5e-3
     gamma = 0.99
-    episodes = 450
+    episodes = 500
 
     # Environment setup
     env = gym.make("CartPole-v1")  # , render_mode="human")