List your company
ResearchFormerly WizWand

H1balance_hard on Humanoid-Bench

73Total Average ReturnDual-Flow RL
37.6446.825665.18Jun 29, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Dual-Flow RL2026.0673
BRO2026.0659
QVPO2026.0657
TD32026.0656
FlowRL2026.0655
SAC2026.0654
QSM2026.0650
D4PG2026.0649
MPO2026.0649
BRO-Fast2026.0647
DDPG2026.0646
A2C2026.0646
TRPO2026.0639