---
tags:
- Pong-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: Pong-v4
      type: Pong-v4
    metrics:
    - type: mean_reward
      value: 3.40 +/- 6.39
      name: mean_reward
      verified: false
---

# (CleanRL) **DQN** Agent Playing **Pong-v4**

This is a trained model of a DQN agent playing Pong-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/DQPN_p1_pt0.1_tt0.1.py).

## Get Started

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

```
pip install "cleanrl[DQPN_p1_pt0.1_tt0.1]"
python -m cleanrl_utils.enjoy --exp-name DQPN_p1_pt0.1_tt0.1 --env-id Pong-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/pfunk/Pong-v4-DQPN_p1_pt0.1_tt0.1-seed1/raw/main/dqpn_atari.py
curl -OL https://huggingface.co/pfunk/Pong-v4-DQPN_p1_pt0.1_tt0.1-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/Pong-v4-DQPN_p1_pt0.1_tt0.1-seed1/raw/main/poetry.lock
poetry install --all-extras
python dqpn_atari.py --exp-name DQPN_p1_pt0.1_tt0.1 --start-policy-f 1000 --end-policy-f 1000 --evaluation-fraction 1.00 --target-tau 0.1 --policy-tau 0.1 --track --wandb-entity pfunk --wandb-project-name dqpn --save-model true --upload-model true --hf-entity pfunk --env-id Pong-v4 --seed 1 --total-timesteps 10000000
```

# Hyperparameters
```python
{'batch_size': 32,
 'buffer_size': 1000000,
 'capture_video': False,
 'cuda': True,
 'end_e': 0.01,
 'end_policy_f': 1000,
 'env_id': 'Pong-v4',
 'evaluation_fraction': 1.0,
 'exp_name': 'DQPN_p1_pt0.1_tt0.1',
 'exploration_fraction': 0.1,
 'gamma': 0.99,
 'hf_entity': 'pfunk',
 'learning_rate': 0.0001,
 'learning_starts': 80000,
 'policy_tau': 0.1,
 'save_model': True,
 'seed': 1,
 'start_e': 1,
 'start_policy_f': 1000,
 'target_network_frequency': 1000,
 'target_tau': 0.1,
 'torch_deterministic': True,
 'total_timesteps': 10000000,
 'track': True,
 'train_frequency': 4,
 'upload_model': True,
 'wandb_entity': 'pfunk',
 'wandb_project_name': 'dqpn'}
```