Downloads · 30 days
0
SpaceInvadersNoFrameskip-v4-dqn_atari_e-2
mallycrip/SpaceInvadersNoFrameskip-v4-dqn_atari_e-2
SpaceInvadersNoFrameskip-v4-dqn_atari_e-2 is a reinforcement learning model from mallycrip. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for cleanrl.
Access
Public
Updated Feb 7, 2023
Repo size
2.4 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp42.2 MB · 87%
At a glance
- Task
- Reinforcement Learning
- Library
- cleanrl
- Access
- Public
- Created
- Feb 7, 2023
- Updated
- Feb 7, 2023
- SHA
- 39bb2813
Model card
From the Hugging Face model README
DQN SpaceInvadersNoFrameskip-v4
Hyperparameters
{'batch_size': 32,
'buffer_size': 100000,
'capture_video': False,
'cuda': True,
'end_e': 0.01,
'env_id': 'SpaceInvadersNoFrameskip-v4',
'exp_name': 'dqn_atari_e',
'exploration_fraction': 0.1,
'gamma': 0.99,
'hf_entity': 'mallycrip',
'learning_rate': 0.0001,
'learning_starts': 80000,
'save_model': False,
'seed': 1,
'start_e': 1,
'target_network_frequency': 1000,
'tau': 1.0,
'torch_deterministic': True,
'total_timesteps': 10000000,
'track': False,
'train_frequency': 4,
'upload_model': True,
'wandb_entity': None,
'wandb_project_name': 'cleanRL'}
- Task
- Reinforcement Learning
- Library
- cleanrl
- Created
- Feb 7, 2023
- Updated
- Feb 7, 2023