mmorales34's picture
pushing model
733b3a6
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: 496.52 +/- 0.00
            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.

Get Started

To use this model, please install the cleanrl package with the following command:

pip install "cleanrl[CP_DQN_norm_1]"
python -m cleanrl_utils.enjoy --exp-name CP_DQN_norm_1 --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-CP_DQN_norm_1-seed355/raw/main/dqn.py
curl -OL https://huggingface.co/pfunk/CartPole-v1-CP_DQN_norm_1-seed355/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/CartPole-v1-CP_DQN_norm_1-seed355/raw/main/poetry.lock
poetry install --all-extras
python dqn.py --track --wandb-entity pfunk --wandb-project-name dqpn --capture-video true --save-model true --upload-model true --hf-entity pfunk --exp-name CP_DQN_norm_1 --max-gradient-norm 1.0 --seed 355

Hyperparameters

{'alg_type': 'dqn.py',
 'batch_size': 256,
 'buffer_size': 300000,
 'capture_video': True,
 'cuda': True,
 'end_e': 0.1,
 'env_id': 'CartPole-v1',
 'exp_name': 'CP_DQN_norm_1',
 'exploration_fraction': 0.2,
 'gamma': 1.0,
 'hf_entity': 'pfunk',
 'learning_rate': 0.0001,
 'learning_starts': 1000,
 'max_gradient_norm': 1.0,
 'save_model': True,
 'seed': 355,
 'start_e': 1.0,
 'target_network_frequency': 100,
 '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'}