metadata

library_name: stable-baselines3
tags:
  - LunarLander-v2
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: 279.70 +/- 19.15
            name: mean_reward
            verified: false

PPO Agent playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library.

Usage (with Stable-baselines3)

# 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 = 512, 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=2000000)

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=278.41 +/- 14.115160134853491
...

Diffs

Dropped n_steps to 512 again
Bumped total_timesteps to 2,000,000