(CleanRL) PPO Agent Playing Breakout-v5
This is a trained model of a PPO agent playing Breakout-v5. 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[jax,envpool,atari]"
python -m cleanrl_utils.enjoy --exp-name cleanba_impala_envpool_machado_atari_wrapper --env-id Breakout-v5
Please refer to the documentation for more detail.
Command to reproduce the training
curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-cleanba_impala_envpool_machado_atari_wrapper-seed1/raw/main/cleanba_impala_envpool_machado_atari_wrapper.py
curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-cleanba_impala_envpool_machado_atari_wrapper-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-cleanba_impala_envpool_machado_atari_wrapper-seed1/raw/main/poetry.lock
poetry install --all-extras
python cleanba_impala_envpool_machado_atari_wrapper.py --save-model --upload-model --total-timesteps 20000
Hyperparameters
{'actor_device_ids': [0],
'actor_devices': ['gpu:0'],
'anneal_lr': True,
'async_batch_size': 60,
'async_update': 1,
'batch_size': 1200,
'capture_video': False,
'cuda': True,
'distributed': False,
'ent_coef': 0.01,
'env_id': 'Breakout-v5',
'exp_name': 'cleanba_impala_envpool_machado_atari_wrapper',
'gamma': 0.99,
'global_learner_decices': ['gpu:0'],
'hf_entity': '',
'learner_device_ids': [0],
'learner_devices': ['gpu:0'],
'learning_rate': 0.00025,
'local_batch_size': 1200,
'local_minibatch_size': 600,
'local_num_envs': 60,
'local_rank': 0,
'max_grad_norm': 0.5,
'minibatch_size': 600,
'num_envs': 60,
'num_minibatches': 2,
'num_steps': 20,
'num_updates': 16,
'profile': False,
'save_model': True,
'seed': 1,
'target_kl': None,
'test_actor_learner_throughput': False,
'torch_deterministic': True,
'total_timesteps': 20000,
'track': False,
'upload_model': True,
'vf_coef': 0.5,
'wandb_entity': None,
'wandb_project_name': 'cleanRL',
'world_size': 1}