You can deploy this model and start earning money today!

cleanrl/
CartPole-v1-c51_jax-seed1

cleanrl

tensorboard

CartPole-v1

deep-reinforcement-learning

reinforcement-learning

custom-implementation

model-index

Views

No views yet

(CleanRL) C51 Agent Playing CartPole-v1

This is a trained model of a C51 agent playing CartPole-v1. 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[c51_jax]"
python -m cleanrl_utils.enjoy --exp-name c51_jax --env-id CartPole-v1

Please refer to the documentation for more detail.

Command to reproduce the training

bash

curl -OL https://huggingface.co/cleanrl/CartPole-v1-c51_jax-seed1/raw/main/c51_jax.py
curl -OL https://huggingface.co/cleanrl/CartPole-v1-c51_jax-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/cleanrl/CartPole-v1-c51_jax-seed1/raw/main/poetry.lock
poetry install --all-extras
python c51_jax.py --save-model --upload-model --hf-entity cleanrl --env-id CartPole-v1

Hyperparameters

python

{'batch_size': 128,
 'buffer_size': 10000,
 'capture_video': False,
 'end_e': 0.05,
 'env_id': 'CartPole-v1',
 'exp_name': 'c51_jax',
 'exploration_fraction': 0.5,
 'gamma': 0.99,
 'hf_entity': 'cleanrl',
 'learning_rate': 0.00025,
 'learning_starts': 10000,
 'n_atoms': 101,
 'save_model': True,
 'seed': 1,
 'start_e': 1,
 'target_network_frequency': 500,
 'total_timesteps': 500000,
 'track': False,
 'train_frequency': 10,
 'upload_model': True,
 'v_max': 100,
 'v_min': -100,
 'wandb_entity': None,
 'wandb_project_name': 'cleanRL'}