Downloads · 30 days
0
my_ppo_LunarLand
EExe/my_ppo_LunarLand
my_ppo_LunarLand is a reinforcement learning model from EExe. 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 May 5, 2023
Repo size
42.5 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp4198 KB · 81%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- May 5, 2023
- Updated
- May 5, 2023
- SHA
- fe108248
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': 'debug'
'gym_id': 'LunarLander-v2'
'hface_repo': 'EExe/my_ppo_LunarLand'
'learning_rate': 0.00025
'seed': 42
'total_timesteps': 2000000
'num_envs': 4
'num_steps': 1024
'gamma': 0.999
'gae_lambda': 0.98
'num_minibatches': 64
'num_epochs': 10
'clip_coeff': 0.2
'ent_coeff': 0.1
'vf_coeff': 0.1
'max_gradient_norm': 0.5
'target_kl': 0.015}
- Task
- Reinforcement Learning
- Created
- May 5, 2023
- Updated
- May 5, 2023