README.md

metadata

library_name: stable-baselines3
tags:
  - LunarLander-v2
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
  - gymnasium
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: 264.37 +/- 27.14
            name: mean_reward
            verified: false
license: mit
language:
  - en
pipeline_tag: reinforcement-learning

PPO Agent playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library. It also represents my first attempt to effectively train a RL agent using StableBaselines3 and Gymnasium, done during the 🤗 Deep Reinforcement Learning Course.

Usage (with Stable-baselines3)

import gymnasium as gym

from huggingface_sb3 import load_from_hub

from stable_baselines3 import PPO
from stable_baselines3.common.monitor import Monitor
from stable_baselines3.common.evaluation import evaluate_policy


repo_id = "Mattizza/PPO-LunarLander-v2_v0__DeepRLCourse"
filename = "ppo-LunarLander-v2_v0.zip"

checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint, print_system_info=True)

# Evaluate the agent
eval_env = Monitor(gym.make("LunarLander-v2"))
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")