(CleanRL) DQPN_freq Agent Playing CartPole-v1
This is a trained model of a DQPN_freq 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_freq_200]"
python -m cleanrl_utils.enjoy --exp-name DQPN_freq_200 --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_freq_200-seed2/raw/main/dqpn_freq.py
curl -OL https://huggingface.co/pfunk/CartPole-v1-DQPN_freq_200-seed2/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/CartPole-v1-DQPN_freq_200-seed2/raw/main/poetry.lock
poetry install --all-extras
python dqpn_freq.py --track --wandb-entity pfunk --wandb-project-name dqpn --capture-video true --save-model true --upload-model true --hf-entity pfunk --exp-name DQPN_freq_200 --policy-network-frequency 200 --seed 2
Hyperparameters
{'alg_type': 'dqpn_freq.py',
'batch_size': 256,
'buffer_size': 300000,
'capture_video': True,
'cuda': True,
'end_e': 0.1,
'env_id': 'CartPole-v1',
'exp_name': 'DQPN_freq_200',
'exploration_fraction': 0.2,
'gamma': 1.0,
'hf_entity': 'pfunk',
'learning_rate': 0.0001,
'learning_starts': 1000,
'policy_network_frequency': 200,
'policy_tau': 1.0,
'save_model': True,
'seed': 2,
'start_e': 1.0,
'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'}
Evaluation results
- mean_reward on CartPole-v1self-reported500.00 +/- 0.00