Downloads · 30 days
0
ppo2
vwxyzjn/ppo2
ppo2 is a reinforcement learning model from vwxyzjn. 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 CartPole-v1. The model was trained by using CleanRL and the training code can be found here.
Access
Public
Updated Oct 13, 2022
Repo size
43.6 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth40.1 KB · 58%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Oct 13, 2022
- Updated
- Oct 13, 2022
- SHA
- 86408bc4
Model card
From the Hugging Face model README
(CleanRL) PPO Agent Playing CartPole-v1
This is a trained model of a PPO agent playing CartPole-v1. The model was trained by using CleanRL and the training code can be found here.
Hyperparameters
{'anneal_lr': True,
'batch_size': 512,
'capture_video': True,
'clip_coef': 0.2,
'clip_vloss': True,
'cuda': False,
'ent_coef': 0.01,
'env_id': 'CartPole-v1',
'exp_name': 'ppo',
'gae_lambda': 0.95,
'gamma': 0.99,
'hf_repo_id': 'vwxyzjn/ppo2',
'learning_rate': 0.00025,
'max_grad_norm': 0.5,
'minibatch_size': 128,
'norm_adv': True,
'num_envs': 4,
'num_minibatches': 4,
'num_steps': 128,
'save_model': True,
'seed': 1,
'target_kl': None,
'torch_deterministic': True,
'total_timesteps': 500000,
'track': False,
'update_epochs': 4,
'vf_coef': 0.5,
'wandb_entity': None,
'wandb_project_name': 'cleanRL'}
- Task
- Reinforcement Learning
- Created
- Oct 13, 2022
- Updated
- Oct 13, 2022