README.md

metadata

tags:
  - CartPole-v1
  - deep-reinforcement-learning
  - reinforcement-learning
  - custom-implementation
library_name: cleanrl
model-index:
  - name: DQN
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: CartPole-v1
          type: CartPole-v1
        metrics:
          - type: mean_reward
            value: 36.50 +/- 11.32
            name: mean_reward
            verified: false

(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.

Command to reproduce the training

curl -OL https://huggingface.co/vwxyzjn/CartPole-v1-dqn_jax-seed1/raw/main/dqn.py
curl -OL https://huggingface.co/vwxyzjn/CartPole-v1-dqn_jax-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/vwxyzjn/CartPole-v1-dqn_jax-seed1/raw/main/poetry.lock
poetry install --all-extras
python dqn_jax.py --save-model --upload-model --hf-entity vwxyzjn --total-timesteps 1000

Hyperparameters

{'batch_size': 128,
 'buffer_size': 10000,
 'capture_video': False,
 'end_e': 0.05,
 'env_id': 'CartPole-v1',
 'exp_name': 'dqn_jax',
 'exploration_fraction': 0.5,
 'gamma': 0.99,
 'hf_entity': 'vwxyzjn',
 'learning_rate': 0.00025,
 'learning_starts': 10000,
 'save_model': True,
 'seed': 1,
 'start_e': 1,
 'target_network_frequency': 500,
 'total_timesteps': 1000,
 'track': False,
 'train_frequency': 10,
 'upload_model': True,
 'wandb_entity': None,
 'wandb_project_name': 'cleanRL'}