You can deploy this model and start earning money today!

pfunk/
CartPole-v1-DQN_baseline_gdrl-seed1

Name: CartPole-v1-DQN_baseline_gdrl-seed1
Availability: InStock

cleanrl

tensorboard

CartPole-v1

deep-reinforcement-learning

reinforcement-learning

custom-implementation

model-index

Views

No views yet

(CleanRL) DQN Agent Playing CartPole-v1

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

Please refer to the documentation for more detail.

Command to reproduce the training

bash

curl -OL https://huggingface.co/pfunk/CartPole-v1-DQN_baseline_gdrl-seed1/raw/main/dqn.py
curl -OL https://huggingface.co/pfunk/CartPole-v1-DQN_baseline_gdrl-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/CartPole-v1-DQN_baseline_gdrl-seed1/raw/main/poetry.lock
poetry install --all-extras
python dqn.py --exp-name DQN_baseline_gdrl --track --wandb-entity pfunk --wandb-project-name dqpn --save-model true --upload-model true --hf-entity pfunk --total-timesteps 500000

Hyperparameters

python

{'batch_size': 64,
 'buffer_size': 50000,
 'capture_video': False,
 'cuda': True,
 'end_e': 0.3,
 'env_id': 'CartPole-v1',
 'exp_name': 'DQN_baseline_gdrl',
 'exploration_fraction': 0.2,
 'gamma': 1.0,
 'hf_entity': 'pfunk',
 'learning_rate': 0.0005,
 'learning_starts': 500,
 'save_model': True,
 'seed': 1,
 'start_e': 1,
 'target_network_frequency': 10,
 'tau': 1.0,
 'torch_deterministic': True,
 'total_timesteps': 500000,
 'track': True,
 'train_frequency': 1,
 'upload_model': True,
 'wandb_entity': 'pfunk',
 'wandb_project_name': 'dqpn'}