odiaz1066's picture
pushing model
23555fd
metadata
tags:
  - LunarLander-v2
  - deep-reinforcement-learning
  - reinforcement-learning
  - custom-implementation
library_name: cleanrl
model-index:
  - name: DQN
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: 227.09 +/- 33.24
            name: mean_reward
            verified: false

(CleanRL) DQN Agent Playing LunarLander-v2

This is a trained model of a DQN agent playing LunarLander-v2. 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[LunarLander-Show]"
python -m cleanrl_utils.enjoy --exp-name LunarLander-Show --env-id LunarLander-v2

Please refer to the documentation for more detail.

Command to reproduce the training

curl -OL https://huggingface.co/odiaz1066/LunarLander-v2-LunarLander-Show-seed42/raw/main/dqn.py
curl -OL https://huggingface.co/odiaz1066/LunarLander-v2-LunarLander-Show-seed42/raw/main/pyproject.toml
curl -OL https://huggingface.co/odiaz1066/LunarLander-v2-LunarLander-Show-seed42/raw/main/poetry.lock
poetry install --all-extras
python dqn.py --track --save-model --capture-video --exp-name LunarLander-Show --seed 42 --env-id LunarLander-v2 --upload-model --hf-entity odiaz1066

Hyperparameters

{'batch_size': 128,
 'buffer_size': 10000,
 'capture_video': True,
 'cuda': True,
 'end_e': 0.05,
 'env_id': 'LunarLander-v2',
 'exp_name': 'LunarLander-Show',
 'exploration_fraction': 0.5,
 'gamma': 0.99,
 'hf_entity': 'odiaz1066',
 'learning_rate': 0.00025,
 'learning_starts': 10000,
 'num_envs': 1,
 'save_model': True,
 'seed': 42,
 'start_e': 1,
 'target_network_frequency': 500,
 'tau': 1.0,
 'torch_deterministic': True,
 'total_timesteps': 500000,
 'track': True,
 'train_frequency': 10,
 'upload_model': True,
 'wandb_entity': None,
 'wandb_project_name': 'lagomorph'}