Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Control Task on Lunar Lander (test)

255.57Average Reward

PPO

-241.0924-112.151216.79145.7312Aug 7, 2025Sep 6, 2025Oct 6, 2025Nov 6, 2025Dec 6, 2025Jan 5, 2026Feb 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
255.57
2026.02
224.43
2026.02
184.16
2026.02
139.17
2025.08
0.846
2025.08
0.819
2025.08
0.776
2025.08
0.653
2025.08
0.508
2026.02
-186.53
2026.02
-221.99