StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks

Benchmark Model Rank Results
robot-manipulation-on-libero-longStructRL (GR00T-N1.5)#27Success Rate: 96.6
robot-manipulation-on-libero-objectStructRL (GR00T-N1.5)#45Success Rate: 99.4
robot-manipulation-on-libero-goalStructRL (GR00T-N1.5)#76Success Rate: 95.6
robot-manipulation-on-libero-spatialStructRL (GR00T-N1.5)#92Success Rate: 92.1