sdpkjc's picture
pushing model
fa60d30
---
tags:
- Walker2d-v4
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DDPG
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Walker2d-v4
type: Walker2d-v4
metrics:
- type: mean_reward
value: 1129.42 +/- 1251.17
name: mean_reward
verified: false
---
# (CleanRL) **DDPG** Agent Playing **Walker2d-v4**
This is a trained model of a DDPG agent playing Walker2d-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/ddpg_continuous_action.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[ddpg_continuous_action]"
python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action --env-id Walker2d-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/cleanrl/Walker2d-v4-ddpg_continuous_action-seed1/raw/main/ddpg_continuous_action.py
curl -OL https://huggingface.co/cleanrl/Walker2d-v4-ddpg_continuous_action-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/cleanrl/Walker2d-v4-ddpg_continuous_action-seed1/raw/main/poetry.lock
poetry install --all-extras
python ddpg_continuous_action.py --track --capture-video --save-model --hf-entity cleanrl --upload-model --env-id Walker2d-v4 --seed 1
```
# Hyperparameters
```python
{'batch_size': 256,
'buffer_size': 1000000,
'capture_video': True,
'cuda': True,
'env_id': 'Walker2d-v4',
'exp_name': 'ddpg_continuous_action',
'exploration_noise': 0.1,
'gamma': 0.99,
'hf_entity': 'cleanrl',
'learning_rate': 0.0003,
'learning_starts': 25000.0,
'noise_clip': 0.5,
'policy_frequency': 2,
'save_model': True,
'seed': 1,
'tau': 0.005,
'torch_deterministic': True,
'total_timesteps': 1000000,
'track': True,
'upload_model': True,
'wandb_entity': None,
'wandb_project_name': 'cleanRL'}
```