zhuqi's picture
Update README.md
9fea0e4
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: 284.96 +/- 22.41
            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.

Training

from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env

env = make_vec_env("LunarLander-v2", n_envs=16)
model = PPO('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)
model.learn(total_timesteps=10000000, progress_bar=True)

Usage (with Stable-baselines3)

from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub

repo_id = "zhuqi/PPO_LunarLander-v2_steps10M"  # The repo_id
filename = "PPO_LunarLander-v2_steps10000000.zip"  # The model filename.zip

# When the model was trained on Python 3.8 the pickle protocol is 5
# But Python 3.6, 3.7 use protocol 4
# In order to get compatibility we need to:
# 1. Install pickle5 (we done it at the beginning of the colab)
# 2. Create a custom empty object we pass as parameter to PPO.load()
custom_objects = {
    "learning_rate": 0.0,
    "lr_schedule": lambda _: 0.0,
    "clip_range": lambda _: 0.0,
}

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