metadata

tags:
  - HalfCheetah-v4
  - deep-reinforcement-learning
  - reinforcement-learning
  - custom-implementation
library_name: cleanrl
model-index:
  - name: DDPG
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: HalfCheetah-v4
          type: HalfCheetah-v4
        metrics:
          - type: mean_reward
            value: 10913.84 +/- 141.94
            name: mean_reward
            verified: false

(CleanRL) DDPG Agent Playing HalfCheetah-v4

This is a trained model of a DDPG agent playing HalfCheetah-v4. The model was trained by using CleanRL and the most up-to-date training code can be found here.

Get Started

To use this model, please install the cleanrl package with the following command:

pip install "cleanrl[ddpg_continuous_action_jax]"
python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action_jax --env-id HalfCheetah-v4

Please refer to the documentation for more detail.

Command to reproduce the training

curl -OL https://huggingface.co/cleanrl/HalfCheetah-v4-ddpg_continuous_action_jax-seed1/raw/main/ddpg_continuous_action_jax.py
curl -OL https://huggingface.co/cleanrl/HalfCheetah-v4-ddpg_continuous_action_jax-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/cleanrl/HalfCheetah-v4-ddpg_continuous_action_jax-seed1/raw/main/poetry.lock
poetry install --all-extras
python ddpg_continuous_action_jax.py --track --capture-video --save-model --hf-entity cleanrl --upload-mode --env-id HalfCheetah-v4 --seed 1

Hyperparameters

{'batch_size': 256,
 'buffer_size': 1000000,
 'capture_video': True,
 'env_id': 'HalfCheetah-v4',
 'exp_name': 'ddpg_continuous_action_jax',
 'exploration_noise': 0.1,
 'gamma': 0.99,
 'hf_entity': 'cleanrl',
 'learning_rate': 0.0003,
 'learning_starts': 25000.0,
 'noise_clip': 0.5,
 'policy_frequency': 2,
 'save_model': True,
 'seed': 1,
 'tau': 0.005,
 'total_timesteps': 1000000,
 'track': True,
 'upload_model': True,
 'wandb_entity': None,
 'wandb_project_name': 'cleanRL'}