Downloads · 30 days
0
ppo-scratch-LunarLander-v2
rondahahda/ppo-scratch-LunarLander-v2
ppo-scratch-LunarLander-v2 is a reinforcement learning model from rondahahda. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
A PPO agent written from scratch (CleanRL style) for the Hugging Face Deep RL Course, Unit 8 part 1.
Access
Public
Updated Sep 24, 2026
Repo size
43.3 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt43.3 KB · 81%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026
- SHA
- 49c8da6d
Model card
From the Hugging Face model README
PPO Agent Playing LunarLander-v2
A PPO agent written from scratch (CleanRL style) for the Hugging Face Deep RL Course, Unit 8 part 1.
Hyperparameters
{
"env_id": "LunarLander-v2",
"seed": 1,
"total_timesteps": 1000000,
"learning_rate": 0.00025,
"num_envs": 8,
"num_steps": 256,
"gamma": 0.99,
"gae_lambda": 0.95,
"num_minibatches": 4,
"update_epochs": 4,
"clip_coef": 0.2,
"ent_coef": 0.01,
"vf_coef": 0.5,
"max_grad_norm": 0.5
}
- Task
- Reinforcement Learning
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026