(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[sebulba_ppo_envpool]"
python -m cleanrl_utils.enjoy --exp-name sebulba_ppo_envpool --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-sebulba_ppo_envpool-seed1/raw/main/sebulba_ppo_envpool.py
curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-sebulba_ppo_envpool-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-sebulba_ppo_envpool-seed1/raw/main/poetry.lock
poetry install --all-extras
python sebulba_ppo_envpool.py --total-timesteps 10000 --save-model --upload-model
Hyperparameters
{'actor_device_ids': [0],
'anneal_lr': True,
'async_batch_size': 16,
'async_update': 4,
'batch_size': 2048,
'capture_video': False,
'clip_coef': 0.1,
'cuda': True,
'ent_coef': 0.01,
'env_id': 'Breakout-v5',
'exp_name': 'sebulba_ppo_envpool',
'gae_lambda': 0.95,
'gamma': 0.99,
'hf_entity': '',
'learner_device_ids': [0],
'learning_rate': 0.00025,
'max_grad_norm': 0.5,
'minibatch_size': 1024,
'norm_adv': True,
'num_actor_threads': 1,
'num_envs': 64,
'num_minibatches': 2,
'num_steps': 32,
'num_updates': 4,
'params_queue_timeout': None,
'profile': False,
'save_model': True,
'seed': 1,
'target_kl': None,
'test_actor_learner_throughput': False,
'torch_deterministic': True,
'total_timesteps': 10000,
'track': False,
'update_epochs': 2,
'upload_model': True,
'vf_coef': 0.5,
'wandb_entity': None,
'wandb_project_name': 'cleanRL'}