README.md

---
tags:
- ALE/Pong-v5
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DQN
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: ALE/Pong-v5
      type: ALE/Pong-v5
    metrics:
    - type: mean_reward
      value: -21.00 +/- 0.00
      name: mean_reward
      verified: false
---

# (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](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/Pong_test.py).

## 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](https://docs.cleanrl.dev/get-started/zoo/) for more detail.


## Command to reproduce the training

```bash
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
```python
{'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'}
```