You can deploy this model and start earning money today!

jacksonhack/
Hopper-v5-ddpg_eval-seed1

Name: Hopper-v5-ddpg_eval-seed1
Availability: InStock

cleanrl

tensorboard

Hopper-v5

deep-reinforcement-learning

reinforcement-learning

custom-implementation

model-index

Views

No views yet

(CleanRL) DDPG Agent Playing Hopper-v5

This is a trained model of a DDPG agent playing Hopper-v5. The model was trained by using CleanRL and the most up-to-date training code can be found here.

Get Started

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

pip install "cleanrl[ddpg_eval]"
python -m cleanrl_utils.enjoy --exp-name ddpg_eval --env-id Hopper-v5

Please refer to the documentation for more detail.

Command to reproduce the training

bash

curl -OL https://huggingface.co/jacksonhack/Hopper-v5-ddpg_eval-seed1/raw/main/ddpg_eval.py
curl -OL https://huggingface.co/jacksonhack/Hopper-v5-ddpg_eval-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/jacksonhack/Hopper-v5-ddpg_eval-seed1/raw/main/poetry.lock
poetry install --all-extras
python ddpg_eval.py 

Hyperparameters

python

{'batch_size': 256,
 'buffer_size': 1000000,
 'capture_video': False,
 'cuda': True,
 'env_id': 'Hopper-v5',
 'exp_name': 'ddpg_eval',
 'exploration_noise': 0.1,
 'gamma': 0.99,
 'hf_entity': 'jacksonhack',
 'learning_rate': 0.0003,
 'learning_starts': 25000.0,
 'noise_clip': 0.5,
 'policy_frequency': 2,
 'save_model': False,
 'seed': 1,
 'tau': 0.005,
 'torch_deterministic': True,
 'total_timesteps': 1000000,
 'track': False,
 'upload_model': False,
 'wandb_entity': None,
 'wandb_project_name': 'cleanRL'}