(CleanRL) DQN Agent Playing ALE/Pong-v5
This is a trained model of a DQN agent playing ALE/Pong-v5. 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[Pong_test]"
python -m cleanrl_utils.enjoy --exp-name Pong_test --env-id ALE/Pong-v5
Please refer to the documentation for more detail.
Command to reproduce the training
curl -OL https://huggingface.co/cotran2/Pong_test/raw/main/dqn_atari.py
curl -OL https://huggingface.co/cotran2/Pong_test/raw/main/pyproject.toml
curl -OL https://huggingface.co/cotran2/Pong_test/raw/main/poetry.lock
poetry install --all-extras
python dqn_atari.py --exp-name Pong_test --track --wandb-project-name pong_test --capture-video --env-id ALE/Pong-v5 --total-timesteps 100000 --buffer-size 400000 --save-model True --upload-model True --hf-entity cotran2
Hyperparameters
{'batch_size': 32,
'buffer_size': 400000,
'capture_video': True,
'cuda': True,
'end_e': 0.01,
'env_id': 'ALE/Pong-v5',
'exp_name': 'Pong_test',
'exploration_fraction': 0.1,
'gamma': 0.99,
'hf_entity': 'cotran2',
'learning_rate': 0.0001,
'learning_starts': 80000,
'num_envs': 1,
'save_model': True,
'seed': 1,
'start_e': 1,
'target_network_frequency': 1000,
'tau': 1.0,
'torch_deterministic': True,
'total_timesteps': 100000,
'track': True,
'train_frequency': 4,
'upload_model': True,
'wandb_entity': None,
'wandb_project_name': 'pong_test'}
Evaluation results
- mean_reward on ALE/Pong-v5self-reported-21.00 +/- 0.00