qgallouedec/BreakoutNoFrameskip-v4-rainbow_atari-seed1

(CleanRL) RAINBOW Agent Playing BreakoutNoFrameskip-v4

This is a trained model of a RAINBOW agent playing BreakoutNoFrameskip-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[rainbow_atari]"
python -m cleanrl_utils.enjoy --exp-name rainbow_atari --env-id BreakoutNoFrameskip-v4

Please refer to the documentation for more detail.

Command to reproduce the training

curl -OL https://huggingface.co/qgallouedec/BreakoutNoFrameskip-v4-rainbow_atari-seed1/raw/main/rainbow_atari.py
curl -OL https://huggingface.co/qgallouedec/BreakoutNoFrameskip-v4-rainbow_atari-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/qgallouedec/BreakoutNoFrameskip-v4-rainbow_atari-seed1/raw/main/poetry.lock
poetry install --all-extras
python rainbow_atari.py --learning-starts 100 --total-timesteps 5000 --save-model --upload-model --hf-entity qgallouedec

Hyperparameters

{'batch_size': 32,
 'buffer_size': 1000000,
 'capture_video': False,
 'cuda': True,
 'env_id': 'BreakoutNoFrameskip-v4',
 'exp_name': 'rainbow_atari',
 'gamma': 0.99,
 'hf_entity': 'qgallouedec',
 'learning_rate': 0.00025,
 'learning_starts': 100,
 'n_atoms': 51,
 'num_envs': 1,
 'save_model': True,
 'seed': 1,
 'target_network_frequency': 10000,
 'torch_deterministic': True,
 'total_timesteps': 5000,
 'track': False,
 'train_frequency': 4,
 'upload_model': True,
 'v_max': 10,
 'v_min': -10,
 'wandb_entity': None,
 'wandb_project_name': 'cleanRL'}