List your company

Continuous Control on Humanoid v5

5,906.7Average ReturnDBC
2,971.33,733.3754,495.455,257.525Feb 5, 2026Feb 15, 2026Feb 26, 2026Mar 9, 2026Mar 19, 2026Mar 30, 2026Apr 10, 2026

Evaluation results

MethodLinks
DBCActor Backbone=SAC2026.025,906.7
TRFP(ours)NFE=4 × 42026.045,370.8
SACNFE=12026.045,350.5
TRFP(one-step)NFE=1 × 42026.045,332.5
TQCActor Backbone=SAC2026.025,269
SACActor Backbone=SAC2026.025,207.1
TD3NFE=12026.045,138.6
VFActor Backbone=SAC2026.024,950.3
VDActor Backbone=SAC2026.024,886.9
IQNActor Backbone=SAC2026.024,729.2
SDACNFE=20 × 322026.044,087.9
DSACActor Backbone=SAC2026.023,442.6
MaxEntDPNFE=20 × 102026.043,084.2