Ppo LunarLander V2

🚀 PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2, leveraging the stable-baselines3 library and the RL Zoo. The RL Zoo offers a training framework for Stable Baselines3 reinforcement learning agents, featuring hyperparameter optimization and pre-trained agents.

🚀 Quick Start

This trained PPO agent is designed to play the LunarLander-v2 environment. It utilizes the stable-baselines3 library and the RL Zoo.

✨ Features

• Trained Model: A pre - trained PPO agent for the LunarLander - v2 environment.
• RL Zoo Integration: Utilizes the RL Zoo for training and hyperparameter optimization.

📦 Installation

The RL Zoo and Stable - Baselines3 libraries are required for using this model. You can access them through the following links:

• 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 LunarLander-v2 -orga sb3 -f logs/
python enjoy.py --algo ppo --env LunarLander-v2  -f logs/

Advanced Usage

python train.py --algo ppo --env LunarLander-v2 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env LunarLander-v2 -f logs/ -orga sb3

🔧 Technical Details

Model Performance

Hyperparameters

OrderedDict([('batch_size', 64),
             ('ent_coef', 0.01),
             ('gae_lambda', 0.98),
             ('gamma', 0.999),
             ('n_envs', 16),
             ('n_epochs', 4),
             ('n_steps', 1024),
             ('n_timesteps', 1000000.0),
             ('policy', 'MlpPolicy'),
             ('normalize', False)])