Edit model card

DDPG Agent playing Walker2DBulletEnv-v0

This is a trained model of a DDPG agent playing Walker2DBulletEnv-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

# Download model and save it into the logs/ folder
python -m utils.load_from_hub --algo ddpg --env Walker2DBulletEnv-v0 -orga sb3 -f logs/
python enjoy.py --algo ddpg --env Walker2DBulletEnv-v0  -f logs/

Training (with the RL Zoo)

python train.py --algo ddpg --env Walker2DBulletEnv-v0 -f logs/
# Upload the model and generate video (when possible)
python -m utils.push_to_hub --algo ddpg --env Walker2DBulletEnv-v0 -f logs/ -orga sb3

Hyperparameters

OrderedDict([('batch_size', 256),
             ('buffer_size', 1000000),
             ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
             ('gamma', 0.98),
             ('gradient_steps', -1),
             ('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', [1, 'episode']),
             ('normalize', False)])
Downloads last month
0
Video Preview
loading

Evaluation results

  • mean_reward on Walker2DBulletEnv-v0
    self-reported
    1495.73 +/- 612.27