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: 284.85 +/- 18.27
            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)


# Defining model
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)


# Training
model.learn(total_timesteps=2000000)

model_name = "ppo-LunarLander-v2"
model.save(model_name)

# evaluation
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=284.85 +/- 18.270698037778157
...

Diffs

Dropped n_steps down to 512
Bumped total_timestamps up to 2,000,000