README.md

metadata

library_name: stable-baselines3
tags:
  - HalfCheetah-v3
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: SAC
    results:
      - metrics:
          - type: mean_reward
            value: 9564.23 +/- 79.21
            name: mean_reward
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: HalfCheetah-v3
          type: HalfCheetah-v3

SAC Agent playing HalfCheetah-v3

This is a trained model of a SAC agent playing HalfCheetah-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 utils.load_from_hub --algo sac --env HalfCheetah-v3 -orga sb3 -f logs/
python enjoy.py --algo sac --env HalfCheetah-v3  -f logs/

Training (with the RL Zoo)

python train.py --algo sac --env HalfCheetah-v3 -f logs/
# Upload the model and generate video (when possible)
python -m utils.push_to_hub --algo sac --env HalfCheetah-v3 -f logs/ -orga sb3

Hyperparameters

OrderedDict([('learning_starts', 10000),
             ('n_timesteps', 1000000.0),
             ('policy', 'MlpPolicy'),
             ('use_sde', False),
             ('normalize', False)])