README.md

metadata

library_name: stable-baselines3
tags:
  - LunarLander-v2
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: PPO
    results:
      - metrics:
          - type: mean_reward
            value: 291.20 +/- 18.45
            name: mean_reward
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2

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)

Create the environment

env = make_vec_env("LunarLander-v2", n_envs=16)

Defining the model, we use MultiLayerPerceptron (MLPPolicy) because the input is a vector,

if we had frames as input we would use CnnPolicy

model = PPO( policy="MlpPolicy", env=env, n_steps=1024, batch_size=64, n_epochs=4, gamma=0.999, gae_lambda=0.98, ent_coef=0.01, verbose=1, )

Training the model for 3,000,000 timesteps

model.learn(total_timesteps=3000000)

Save the model

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