Adding model

README.md

@@ -30,8 +30,34 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
 
+# https://stackoverflow.com/questions/72483775/stable-baselines3-ppo-how-to-change-clip-range-parameter-during-training
+def lrsched():
+  def reallr(progress):
+    lr = 0.004
+    if progress < 0.85:
+      lr = 0.0005
+    if progress < 0.66:
+      lr = 0.00025
+    if progress < 0.33:
+      lr = 0.0001
+    return lr
+  return reallr
+model = PPO('MlpPolicy', env, n_steps = 1024, batch_size = 64, n_epochs = 4, gamma = 0.999, gae_lambda = 0.98, ent_coef = 0.01, verbose=1, learning_rate=lrsched())
+
+model.learn(total_timesteps=1000000)
+
+model_name = "ppo-LunarLander-v2"
+model.save(model_name)
+
+eval_env = Monitor(gym.make("LunarLander-v2"))
+
+# Evaluate the model with 10 evaluation episodes and deterministic=True
+mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
+
+# Print the results
+print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
+
+# mean_reward=245.30 +/- 50.161170246383584
 ...
 ```