(CleanRL) DQPN_decay Agent Playing CartPole-v1

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

Please refer to the documentation for more detail.

Command to reproduce the training

curl -OL https://huggingface.co/pfunk/CartPole-v1-DQPN_decay-seed1/raw/main/dqpn_decay.py
curl -OL https://huggingface.co/pfunk/CartPole-v1-DQPN_decay-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/CartPole-v1-DQPN_decay-seed1/raw/main/poetry.lock
poetry install --all-extras
python dqpn_decay.py --exp-name DQPN_decay --seed 1 --track --wandb-entity pfunk --wandb-project-name dqpn --capture-video true --save-model true --upload-model true --hf-entity pfunk

Hyperparameters

{'alg_type': 'dqpn_decay.py',
 'batch_size': 256,
 'buffer_size': 300000,
 'capture_video': True,
 'cuda': True,
 'end_e': 0.1,
 'end_policy_network_frequency': 200,
 'env_id': 'CartPole-v1',
 'evaluation_fraction': 0.7,
 'exp_name': 'DQPN_decay',
 'exploration_fraction': 0.2,
 'gamma': 1.0,
 'hf_entity': 'pfunk',
 'learning_rate': 0.0001,
 'learning_starts': 1000,
 'policy_tau': 1.0,
 'save_model': True,
 'seed': 1,
 'start_e': 1.0,
 'start_policy_network_frequency': 10000,
 'target_network_frequency': 20,
 'target_tau': 1.0,
 'torch_deterministic': True,
 'total_timesteps': 500000,
 'track': True,
 'train_frequency': 1,
 'upload_model': True,
 'wandb_entity': 'pfunk',
 'wandb_project_name': 'dqpn'}