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

Reinforcement Learning on Humanoid v4

5,715Reward

C-DSAC

-56.14721,442.13142,940.414,438.6886Apr 26, 2026May 5, 2026May 15, 2026May 24, 2026Jun 3, 2026Jun 12, 2026Jun 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
5,715
2026.06
660
2026.06
660
2026.06
553
2026.05
457.02
2026.05
454.46
2026.05
356.85
2026.06
342
2026.05
284.49
2026.05
250.65
2026.05
221.1
2026.05
218.15
2026.05
165.82