Views
No views yet
cleanrl package with the following command:pip install "cleanrl[jax,envpool,atari]"
python -m cleanrl_utils.enjoy --exp-name sebulba_ppo_envpool_impala_atari_wrapper --env-id Jamesbond-v51curl -OL https://huggingface.co/cleanrl/Jamesbond-v5-sebulba_ppo_envpool_impala_atari_wrapper-seed2/raw/main/sebulba_ppo_envpool_impala_atari_wrapper.py
2curl -OL https://huggingface.co/cleanrl/Jamesbond-v5-sebulba_ppo_envpool_impala_atari_wrapper-seed2/raw/main/pyproject.toml
3curl -OL https://huggingface.co/cleanrl/Jamesbond-v5-sebulba_ppo_envpool_impala_atari_wrapper-seed2/raw/main/poetry.lock
4poetry install --all-extras
5python sebulba_ppo_envpool_impala_atari_wrapper.py --actor-device-ids 0 --learner-device-ids 1 2 3 4 5 6 --track --save-model --upload-model --hf-entity cleanrl --env-id Jamesbond-v5 --seed 21{'actor_device_ids': [0],
2 'anneal_lr': True,
3 'async_batch_size': 20,
4 'async_update': 3,
5 'batch_size': 7680,
6 'capture_video': False,
7 'clip_coef': 0.1,
8 'cuda': True,
9 'ent_coef': 0.01,
10 'env_id': 'Jamesbond-v5',
11 'exp_name': 'sebulba_ppo_envpool_impala_atari_wrapper',
12 'gae_lambda': 0.95,
13 'gamma': 0.99,
14 'hf_entity': 'cleanrl',
15 'learner_device_ids': [1, 2, 3, 4, 5, 6],
16 'learning_rate': 0.00025,
17 'max_grad_norm': 0.5,
18 'minibatch_size': 1920,
19 'norm_adv': True,
20 'num_actor_threads': 1,
21 'num_envs': 60,
22 'num_minibatches': 4,
23 'num_steps': 128,
24 'num_updates': 6510,
25 'profile': False,
26 'save_model': True,
27 'seed': 2,
28 'target_kl': None,
29 'test_actor_learner_throughput': False,
30 'torch_deterministic': True,
31 'total_timesteps': 50000000,
32 'track': True,
33 'update_epochs': 4,
34 'upload_model': True,
35 'vf_coef': 0.5,
36 'wandb_entity': None,
37 'wandb_project_name': 'cleanRL'}