Downloads · 30 days
0
ppo-CartPole-v1
jake-walker/ppo-CartPole-v1
ppo-CartPole-v1 is a reinforcement learning model from jake-walker. 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.
Access
Public
Updated Nov 10, 2023
Repo size
115 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.475.4 KB · 59%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Nov 10, 2023
- Updated
- Nov 10, 2023
- SHA
- 3e974089
Model card
From the Hugging Face model README
PPO Agent Playing CartPole-v1
This is a trained model of a PPO agent playing CartPole-v1.
Hyperparameters
{'exp_name': 'ppo'
'gym_id': 'CartPole-v1'
'learning_rate': 0.00025
'seed': 1
'total_timesteps': 25000
'torch_deterministic': True
'cuda': True
'track': False
'capture_video': False
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_gradient_norm': 0.5
'target_kl': None
'repo_id': 'jake-walker/ppo-CartPole-v1'
'batch_size': 512
'minibatch_size': 128}
- Task
- Reinforcement Learning
- Created
- Nov 10, 2023
- Updated
- Nov 10, 2023