Downloads · 30 days
6
6% of all-time downloads
ppo-LunarLander-v2
YoavWigelman/ppo-LunarLander-v2
ppo-LunarLander-v2 is a reinforcement learning model from YoavWigelman. 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 transformers.
This is a trained model of a PPO agent playing LunarLander-v2.
All-time downloads
102
Public
Repo size
571 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.0251 KB · 33%
At a glance
- Task
- Reinforcement Learning
- Library
- transformers
- Access
- Public
- Created
- May 6, 2023
- Updated
- Aug 5, 2023
- SHA
- aebfb7a5
Model card
From the Hugging Face model README
PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
Hyperparameters
{'exp_name': 'unit8-ppo-LunarLander-v2.2'
'env_id': 'LunarLander-v2'
'learning_rate': 0.00025
'seed': 1
'total_timestamps': 500000
'torch_deterministic': True
'cuda': True
'track': True
'wandb_project_name': 'ppo-implementation-details'
'wandb_entity': None
'capture_video': True
'num_envs': 8
'num_steps': 256
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 8
'update_epochs': 8
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'YoavWigelman/ppo-LunarLander-v2'
'batch_size': 2048
'minibatch_size': 256}
- Task
- Reinforcement Learning
- Library
- transformers
- Created
- May 6, 2023
- Updated
- Aug 5, 2023