mmorales34's picture
pushing model
e8dfebf
---
tags:
- BreakoutNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DQPN_freq
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: BreakoutNoFrameskip-v4
type: BreakoutNoFrameskip-v4
metrics:
- type: mean_reward
value: 154.09 +/- 0.00
name: mean_reward
verified: false
---
# (CleanRL) **DQPN_freq** Agent Playing **BreakoutNoFrameskip-v4**
This is a trained model of a DQPN_freq agent playing BreakoutNoFrameskip-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_DQN.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[DQPN_DQN]"
python -m cleanrl_utils.enjoy --exp-name DQPN_DQN --env-id BreakoutNoFrameskip-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/BreakoutNoFrameskip-v4-DQPN_DQN-seed1/raw/main/dqpn_freq_atari.py
curl -OL https://huggingface.co/pfunk/BreakoutNoFrameskip-v4-DQPN_DQN-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/BreakoutNoFrameskip-v4-DQPN_DQN-seed1/raw/main/poetry.lock
poetry install --all-extras
python dqpn_freq_atari.py --track --wandb-entity pfunk --wandb-project-name dqpn --capture-video true --save-model true --upload-model true --hf-entity pfunk --exp-name DQPN_DQN --target-network-frequency 1000 --policy-network-frequency 1 --seed 1 --env-id BreakoutNoFrameskip-v4
```
# Hyperparameters
```python
{'alg_type': 'dqpn_freq_atari.py',
'batch_size': 32,
'buffer_size': 1000000,
'capture_video': True,
'cuda': True,
'double_learning': False,
'end_e': 0.05,
'env_id': 'BreakoutNoFrameskip-v4',
'exp_name': 'DQPN_DQN',
'exploration_fraction': 0.2,
'gamma': 0.99,
'hf_entity': 'pfunk',
'learning_rate': 0.0001,
'learning_starts': 10000,
'max_gradient_norm': inf,
'policy_network_frequency': 1,
'policy_tau': 1.0,
'save_model': True,
'seed': 1,
'start_e': 1.0,
'target_network_frequency': 1000,
'target_tau': 1.0,
'torch_deterministic': True,
'total_timesteps': 10000000,
'track': True,
'train_frequency': 1,
'upload_model': True,
'wandb_entity': 'pfunk',
'wandb_project_name': 'dqpn'}
```