|
Download README.md from ssw1591/SpaceInvadersNoFrameskip-v4: direct link, hf CLI and curl.
- Browser
- Download file 2.26 kB
-
https://huggingface.co/ssw1591/SpaceInvadersNoFrameskip-v4/resolve/main/README.md
- Command line
-
hf download hf://ssw1591/SpaceInvadersNoFrameskip-v4/README.md
-
curl -L -o README.md https://huggingface.co/ssw1591/SpaceInvadersNoFrameskip-v4/resolve/main/README.md
2.26 kB
| tags: | |
| - SpaceInvadersNoFrameskip-v4 | |
| - deep-reinforcement-learning | |
| - reinforcement-learning | |
| - custom-implementation | |
| library_name: cleanrl | |
| model-index: | |
| - name: DQN | |
| results: | |
| - task: | |
| type: reinforcement-learning | |
| name: reinforcement-learning | |
| dataset: | |
| name: SpaceInvadersNoFrameskip-v4 | |
| type: SpaceInvadersNoFrameskip-v4 | |
| metrics: | |
| - type: mean_reward | |
| value: 523.50 +/- 219.93 | |
| name: mean_reward | |
| verified: false | |
| # (CleanRL) **DQN** Agent Playing **SpaceInvadersNoFrameskip-v4** | |
| This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4. | |
| The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be | |
| found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/dqn_atari.py). | |
| ## Get Started | |
| To use this model, please install the `cleanrl` package with the following command: | |
| ``` | |
| pip install "cleanrl[dqn_atari]" | |
| python -m cleanrl_utils.enjoy --exp-name dqn_atari --env-id SpaceInvadersNoFrameskip-v4 | |
| ``` | |
| Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail. | |
| ## Command to reproduce the training | |
| ```bash | |
| curl -OL https://huggingface.co/ssw1591/SpaceInvadersNoFrameskip-v4/raw/main/dqn_atari.py | |
| curl -OL https://huggingface.co/ssw1591/SpaceInvadersNoFrameskip-v4/raw/main/pyproject.toml | |
| curl -OL https://huggingface.co/ssw1591/SpaceInvadersNoFrameskip-v4/raw/main/poetry.lock | |
| poetry install --all-extras | |
| python dqn_atari.py --env-id SpaceInvadersNoFrameskip-v4 --total-timesteps 1000000 --capture-video --save-model --cuda --upload-model --hf-entity ssw1591 --seed 2 | |
| ``` | |
| # Hyperparameters | |
| ```python | |
| {'batch_size': 32, | |
| 'buffer_size': 1000000, | |
| 'capture_video': True, | |
| 'cuda': True, | |
| 'end_e': 0.01, | |
| 'env_id': 'SpaceInvadersNoFrameskip-v4', | |
| 'exp_name': 'dqn_atari', | |
| 'exploration_fraction': 0.1, | |
| 'gamma': 0.99, | |
| 'hf_entity': 'ssw1591', | |
| 'learning_rate': 0.0001, | |
| 'learning_starts': 80000, | |
| 'save_model': True, | |
| 'seed': 2, | |
| 'start_e': 1, | |
| 'target_network_frequency': 1000, | |
| 'tau': 1.0, | |
| 'torch_deterministic': True, | |
| 'total_timesteps': 1000000, | |
| 'track': False, | |
| 'train_frequency': 4, | |
| 'upload_model': True, | |
| 'wandb_entity': None, | |
| 'wandb_project_name': 'cleanRL'} | |
| ``` | |