Downloads · 30 days
0
ppo-from-scratch-LunarLander-v3
Stilt34/ppo-from-scratch-LunarLander-v3
ppo-from-scratch-LunarLander-v3 is a reinforcement learning model from Stilt34. 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 LunarLandar-v3.
Access
Public
Updated May 27, 2026
Repo size
768 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp4136 KB · 79%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- May 27, 2026
- Updated
- May 27, 2026
- SHA
- 798a1407
Model card
From the Hugging Face model README
PPO Agent Playing LunarLandar-v3
This is a trained model of a PPO agent playing LunarLandar-v3.
Hyperparameters
timesteps=2e6,
steps_before_update=1000,
mini_batch_size=64, epochs=3,
lr=3e-4,
gamma=0.99,
gae_lambda=0.95,
clip_coef=0.2,
norm_adv=True,
vf_coef=0.5,
ent_coef=0.05,
max_grad_norm=1.0,
target_kl=0.015
- Task
- Reinforcement Learning
- Created
- May 27, 2026
- Updated
- May 27, 2026