Downloads · 30 days
0
ppo-LunarLander-v3
hunghd20012003/ppo-LunarLander-v3
ppo-LunarLander-v3 is a machine learning model from hunghd20012003. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was trained using Stable-Baselines3 PPO on LunarLander-v3.
Access
Public
Updated Feb 26, 2026
Repo size
149 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zip149 KB · 62%
At a glance
- Access
- Public
- Created
- Feb 26, 2026
- Updated
- Feb 26, 2026
- SHA
- 050a498a
Model card
From the Hugging Face model README
🚀 PPO LunarLander-v3 Agent
This model was trained using Stable-Baselines3 PPO on LunarLander-v3.
📦 Environment
- Gymnasium LunarLander-v3
- Discrete action space (4 actions)
- Observation space shape: (8,)
🧠 Algorithm
- PPO (Proximal Policy Optimization)
- MlpPolicy
- 200,000 timesteps
- gamma=0.999
- gae_lambda=0.98
📊 Performance
Mean reward after training: >200
🎥 Demo
See replay.mp4 for a sample landing episode.
📥 Load Model
from stable_baselines3 import PPO
model = PPO.load("ppo_lunarlander.zip")
- Created
- Feb 26, 2026
- Updated
- Feb 26, 2026