Downloads · 30 days
0
full-impl-ppo-LunarLander-v2
SakataHalmi/full-impl-ppo-LunarLander-v2
full-impl-ppo-LunarLander-v2 is a reinforcement learning model from SakataHalmi. 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 Oct 9, 2023
Repo size
13.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.013.3 MB · 99%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Oct 8, 2023
- Updated
- Oct 9, 2023
- SHA
- d3b0dd73
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'
'gym_id': 'LunarLander-v2'
'learning_rate': 0.00025
'seed': 1
'total_timesteps': 2000000
'torch_determistic': True
'cuda': True
'track': True
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'num_envs': 4
'num_steps': 128
'anneal_lr': False
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatchs': 4
'update_epochs': 4
'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
'batch_size': 512
'minibatch_size': 128}
- Task
- Reinforcement Learning
- Created
- Oct 8, 2023
- Updated
- Oct 9, 2023