DDPG Agent playing HopperBulletEnv-v0
This is a trained model of a DDPG agent playing HopperBulletEnv-v0 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
Install the RL Zoo (with SB3 and SB3-Contrib):
pip install rl_zoo3
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo ddpg --env HopperBulletEnv-v0 -orga qgallouedec -f logs/
python -m rl_zoo3.enjoy --algo ddpg --env HopperBulletEnv-v0 -f logs/
If you installed the RL Zoo3 via pip (pip install rl_zoo3
), from anywhere you can do:
python -m rl_zoo3.load_from_hub --algo ddpg --env HopperBulletEnv-v0 -orga qgallouedec -f logs/
python -m rl_zoo3.enjoy --algo ddpg --env HopperBulletEnv-v0 -f logs/
Training (with the RL Zoo)
python -m rl_zoo3.train --algo ddpg --env HopperBulletEnv-v0 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ddpg --env HopperBulletEnv-v0 -f logs/ -orga qgallouedec
Hyperparameters
OrderedDict([('batch_size', 256),
('buffer_size', 200000),
('gamma', 0.98),
('gradient_steps', 64),
('learning_rate', 0.0007),
('learning_starts', 10000),
('n_timesteps', 1000000.0),
('noise_std', 0.1),
('noise_type', 'normal'),
('policy', 'MlpPolicy'),
('policy_kwargs', 'dict(net_arch=[400, 300])'),
('train_freq', 64),
('normalize', False)])
- Downloads last month
- 2
Evaluation results
- mean_reward on HopperBulletEnv-v0self-reported994.79 +/- 546.59