Ppo MountainCar V0

🚀 PPO Agent playing MountainCar-v0

This project presents a trained PPO agent for the MountainCar-v0 environment, leveraging the stable-baselines3 library and the RL Zoo. The RL Zoo serves as a training framework for Stable Baselines3 reinforcement learning agents, featuring hyperparameter optimization and pre-trained agents.

🚀 Quick Start

✨ Features

• Utilizes the PPO algorithm to train an agent for the MountainCar-v0 environment.
• Integrates with the stable-baselines3 library and RL Zoo.
• Supports model downloading, training, and uploading.

📦 Installation

This section doesn't explicitly have installation steps, but the usage and training rely on the following repositories:

• RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo
• SB3: https://github.com/DLR-RM/stable-baselines3
• SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib

💻 Usage Examples

Basic Usage

# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo ppo --env MountainCar-v0 -orga sb3 -f logs/
python enjoy.py --algo ppo --env MountainCar-v0  -f logs/

Advanced Usage

python train.py --algo ppo --env MountainCar-v0 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env MountainCar-v0 -f logs/ -orga sb3

📚 Documentation

Hyperparameters

OrderedDict([('ent_coef', 0.0),
             ('gae_lambda', 0.98),
             ('gamma', 0.99),
             ('n_envs', 16),
             ('n_epochs', 4),
             ('n_steps', 16),
             ('n_timesteps', 1000000.0),
             ('normalize', True),
             ('policy', 'MlpPolicy'),
             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])

📄 License

The original README doesn't contain license information, so this section is skipped.

Model Information