Downloads · 30 days
0
ippo-LunarLander-v2
PhysHunter/ippo-LunarLander-v2
ippo-LunarLander-v2 is a reinforcement learning model from PhysHunter. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This is a trained model of a PPO agent playing LunarLander-v2.
Access
Public
Updated Jun 12, 2023
Repo size
9.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.09.1 MB · 98%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Jun 12, 2023
- Updated
- Jun 12, 2023
- SHA
- 23513e4d
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': 'ppo'
'repo_id': 'PhysHunter/ippo-LunarLander-v2'
'env_id': 'LunarLander-v2'
'learning_rate': 0.001
'seed': 1
'total_timesteps': 1000000
'torch_deterministic': True
'cuda': True
'record_video': None
'num_envs': 16
'num_steps': 1024
'anneal_lr': False
'gae_lambda': 0.98
'gamma': 0.999
'minibatch_size': 4096
'num_epochs': 16
'adv_norm': True
'clip_coef': 0.2
'clip_value_loss': True
'entropy_coef': 0.01
'value_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'num_hiddens': 64
'batch_size': 16384}
- Task
- Reinforcement Learning
- Created
- Jun 12, 2023
- Updated
- Jun 12, 2023