Code modified

README.md

@@ -30,24 +30,24 @@ from stable_baselines3 import PPO
 from stable_baselines3.common.evaluation import evaluate_policy
 from stable_baselines3.common.env_util import make_vec_env
 
-# Create a vectorized environment of 16 parallel environments
-env = make_vec_env("LunarLander-v2", n_envs=16)
+# Create a vectorized environment of 64 parallel environments
+env = make_vec_env("LunarLander-v2", n_envs=64)
 
 # Optimizaed Hyperparameters
 model = PPO(
     "MlpPolicy",
     env=env,
-    n_steps=655,
+    n_steps=1024,
     batch_size=32,
-    n_epochs=8,
-    gamma=0.998,
+    n_epochs=10,
+    gamma=0.997,
     gae_lambda=0.98,
     ent_coef=0.01,
     verbose=1,
 )
 
-# Train it for 500,000 timesteps
-model.learn(total_timesteps=int(5e6))
+# Train it for 1,000,000 timesteps
+model.learn(total_timesteps=int(1e6))
 
 # Create a new environment for evaluation
 eval_env = gym.make("LunarLander-v2")
@@ -60,8 +60,6 @@ mean_reward, std_reward = evaluate_policy(
 # Print the results
 print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
 
-#>>> mean_reward=254.56 +/- 18.45056958672337
-
-
+# >>> mean_reward=261.42 +/- 18.69168514436243
   ```