ResearchBenchmarksDexterous Manipulation on ReorientationFollow43.75Average PerformanceCPO-0.668410.863322.39533.9267Mar 2, 2026Evaluation ResultsMethodMethodLinksAverage PerformanceCPOEnvironment steps=2 ×...Environment steps=2 × 10^102026.0343.75SAPGEnvironment steps=2 ×...Environment steps=2 × 10^102026.0338.79PBTEnvironment steps=2 ×...Environment steps=2 × 10^102026.032.92PPOEnvironment steps=2 ×...Environment steps=2 × 10^102026.031.04