ppo-LunarLander-v2 / README.md
smatt92's picture
Update README.md
82b6d11 verified
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: 271.39 +/- 12.49
            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)

TODO: Add your code

Create environment

env = gym.make('LunarLander-v2')

Instantiate the agent

model = PPO('MlpPolicy', env, verbose=1)

Train the agent

model.learn(total_timesteps=int(2e5))

TODO: Define a PPO MlpPolicy architecture

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 = 4096, batch_size = 128, n_epochs = 8, gamma = 0.999, gae_lambda = 0.98, ent_coef = 0.01, verbose=1)

TODO: Train it for 1,000,000 timesteps

model.learn(total_timesteps=2000000)

TODO: Specify file name for model and save the model to file

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

TODO: Evaluate the agent

Create a new environment for 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}")

from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub

...