|
--- |
|
tags: |
|
- Ant-v4 |
|
- deep-reinforcement-learning |
|
- reinforcement-learning |
|
- custom-implementation |
|
library_name: cleanrl |
|
model-index: |
|
- name: SAC |
|
results: |
|
- task: |
|
type: reinforcement-learning |
|
name: reinforcement-learning |
|
dataset: |
|
name: Ant-v4 |
|
type: Ant-v4 |
|
metrics: |
|
- type: mean_reward |
|
value: 4623.14 +/- 1360.99 |
|
name: mean_reward |
|
verified: false |
|
--- |
|
|
|
# (CleanRL) **SAC** Agent Playing **Ant-v4** |
|
|
|
This is a trained model of a SAC agent playing Ant-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/sac_continuous_action.py). |
|
|
|
## Get Started |
|
|
|
To use this model, please install the `cleanrl` package with the following command: |
|
|
|
``` |
|
pip install "cleanrl[sac_continuous_action]" |
|
python -m cleanrl_utils.enjoy --exp-name sac_continuous_action --env-id Ant-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/sdpkjc/Ant-v4-sac_continuous_action-seed5/raw/main/sac_continuous_action.py |
|
curl -OL https://huggingface.co/sdpkjc/Ant-v4-sac_continuous_action-seed5/raw/main/pyproject.toml |
|
curl -OL https://huggingface.co/sdpkjc/Ant-v4-sac_continuous_action-seed5/raw/main/poetry.lock |
|
poetry install --all-extras |
|
python sac_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id Ant-v4 --seed 5 --track |
|
``` |
|
|
|
# Hyperparameters |
|
```python |
|
{'alpha': 0.2, |
|
'autotune': True, |
|
'batch_size': 256, |
|
'buffer_size': 1000000, |
|
'capture_video': False, |
|
'cuda': True, |
|
'env_id': 'Ant-v4', |
|
'exp_name': 'sac_continuous_action', |
|
'gamma': 0.99, |
|
'hf_entity': 'sdpkjc', |
|
'learning_starts': 5000.0, |
|
'noise_clip': 0.5, |
|
'policy_frequency': 2, |
|
'policy_lr': 0.0003, |
|
'q_lr': 0.001, |
|
'save_model': True, |
|
'seed': 5, |
|
'target_network_frequency': 1, |
|
'tau': 0.005, |
|
'torch_deterministic': True, |
|
'total_timesteps': 1000000, |
|
'track': True, |
|
'upload_model': True, |
|
'wandb_entity': None, |
|
'wandb_project_name': 'cleanRL'} |
|
``` |
|
|
