Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
unit8-cleanrl-lunarlander-gpu-course – AI Model by xiamoqiu | AlphaNeural AI
You can deploy this model and start earning money today!
xiamoqiu
/
unit8-cleanrl-lunarlander-gpu-course
like
0
tensorboard
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
LunarLander-v3 PPO Run
Run name: ppo-LunarLander-gpu-course
Run time (UTC): 2026-04-18T08:51:55Z
Device: cuda
Total timesteps: 50000
Num envs: 4
Num steps: 128
Learning rate: 0.00025
Mean eval reward: -1054.7867
Std eval reward: 1284.7071
Evaluation video: replay.mp4