Edit model card

(CleanRL) DQN Agent Playing SpaceInvadersNoFrameskip-v4

This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4. 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[dqn30may_rnd]"
python -m cleanrl_utils.enjoy --exp-name dqn30may_rnd --env-id SpaceInvadersNoFrameskip-v4

Please refer to the documentation for more detail.

Command to reproduce the training

curl -OL https://huggingface.co/FranEnguix/SpaceInvadersNoFrameskip-v4-dqn30may_rnd-seed1/raw/main/dqn_atari.py
curl -OL https://huggingface.co/FranEnguix/SpaceInvadersNoFrameskip-v4-dqn30may_rnd-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/FranEnguix/SpaceInvadersNoFrameskip-v4-dqn30may_rnd-seed1/raw/main/poetry.lock
poetry install --all-extras
python dqn_atari.py --env-id SpaceInvadersNoFrameskip-v4 --track --cuda --total-timesteps 0 --buffer-size 800000 --capture-video --upload-model --hf-entity FranEnguix --exp-name dqn30may_rnd --wandb-project-name arf_final_project --seed 1 --save-model

Hyperparameters

{'batch_size': 32,
 'buffer_size': 800000,
 'capture_video': True,
 'cuda': True,
 'end_e': 0.01,
 'env_id': 'SpaceInvadersNoFrameskip-v4',
 'exp_name': 'dqn30may_rnd',
 'exploration_fraction': 0.1,
 'gamma': 0.99,
 'hf_entity': 'FranEnguix',
 'learning_rate': 0.0001,
 'learning_starts': 80000,
 'num_envs': 1,
 'save_model': True,
 'seed': 1,
 'start_e': 1,
 'target_network_frequency': 1000,
 'tau': 1.0,
 'torch_deterministic': True,
 'total_timesteps': 0,
 'track': True,
 'train_frequency': 4,
 'upload_model': True,
 'wandb_entity': None,
 'wandb_project_name': 'arf_final_project'}
Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading

Evaluation results

  • mean_reward on SpaceInvadersNoFrameskip-v4
    self-reported
    40.50 +/- 23.82