List your company
ResearchFormerly WizWand

H1reach on Humanoid-Bench

6,757Total Average ReturnDual-Flow RL
1,410.362,798.434,186.55,574.57Jun 29, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Dual-Flow RL2026.066,757
FlowRL2026.065,179
TD32026.064,431
QSM2026.064,421
QVPO2026.064,310
SAC2026.063,893
BRO2026.062,323
D4PG2026.062,142
MPO2026.062,015
TRPO2026.061,952
BRO-Fast2026.061,855
DDPG2026.061,686
A2C2026.061,616