List your company

ResearchFormerly WizWand

H1maze on Humanoid-Bench

458Total Average ReturnDual-Flow RL

Evaluation results

Method	Links
Dual-Flow RL2026.06		458
QSM2026.06		420
FlowRL2026.06		389
QVPO2026.06		304
SAC2026.06		294
BRO2026.06		170
TD32026.06		169
D4PG2026.06		156
MPO2026.06		145
TRPO2026.06		143
BRO-Fast2026.06		140
DDPG2026.06		118
A2C2026.06		114