A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning
Hebero and DGPO train one policy across 40 robot tasks, reaching 90.1% success with 50 demos.
2 stories, newest first · one card per story
Hebero and DGPO train one policy across 40 robot tasks, reaching 90.1% success with 50 demos.
DuoOPD uses joint teacher-student outcomes to improve multi-task on-policy distillation over standard OPD.
Today 2.3K readers · 2.8K views · 408 reads · all time 108K views