PPO Agent playing BipedalWalker-v3
This is a trained model of a PPO agent playing BipedalWalker-v3 using the stable-baselines3 library and the RL Zoo.
The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Usage (with SB3 RL Zoo)
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
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo ppo --env BipedalWalker-v3 -orga sb3 -f logs/
python enjoy.py --algo ppo --env BipedalWalker-v3 -f logs/
Training (with the RL Zoo)
python train.py --algo ppo --env BipedalWalker-v3 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env BipedalWalker-v3 -f logs/ -orga sb3
Hyperparameters
OrderedDict([('batch_size', 64),
('clip_range', 0.18),
('ent_coef', 0.0),
('gae_lambda', 0.95),
('gamma', 0.999),
('learning_rate', 0.0003),
('n_envs', 32),
('n_epochs', 10),
('n_steps', 2048),
('n_timesteps', 5000000.0),
('normalize', True),
('policy', 'MlpPolicy'),
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])