|
--- |
|
tags: |
|
- ALE/Pitfall2-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/Pitfall2-v5 |
|
type: ALE/Pitfall2-v5 |
|
metrics: |
|
- type: mean_reward |
|
value: 0.00 +/- 0.00 |
|
name: mean_reward |
|
verified: false |
|
--- |
|
|
|
# (CleanRL) **DQN** Agent Playing **ALE/Pitfall2-v5**
|
|
|
|
This is a trained model of a DQN agent playing ALE/Pitfall2-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/PitFall.py).
|
|
|
|
## Get Started
|
|
|
|
To use this model, please install the `cleanrl` package with the following command:
|
|
|
|
```
|
|
pip install "cleanrl[PitFall]"
|
|
python -m cleanrl_utils.enjoy --exp-name PitFall --env-id ALE/Pitfall2-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/PitFall/raw/main/dqn_atari.py
|
|
curl -OL https://huggingface.co/cotran2/PitFall/raw/main/pyproject.toml
|
|
curl -OL https://huggingface.co/cotran2/PitFall/raw/main/poetry.lock
|
|
poetry install --all-extras
|
|
python dqn_atari.py --exp-name PitFall --track --wandb-project-name PitFall --capture-video --env-id ALE/Pitfall2-v5 --total-timesteps 1000000 --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/Pitfall2-v5',
|
|
'exp_name': 'PitFall',
|
|
'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': 1000000,
|
|
'track': True,
|
|
'train_frequency': 4,
|
|
'upload_model': True,
|
|
'wandb_entity': None,
|
|
'wandb_project_name': 'PitFall'}
|
|
```
|
|
|