Event
MDPO: A Multi-Constraint Dexterous Manipulation Policy Optimization Method
1 reports · 1 sources
Ao Zhou and other authors propose a multi-constraint dexterous policy optimization method, MDPO, which models dexterous manipulation as a multi-constraint policy optimization problem that simultaneously includes cumulative cost constraints and per-state cost constraints, and integrates multi-constraint projection into the policy optimization process. The authors state that in experiments on safe joint control, finger safety, and grasping tasks in ReDMan, MDPO achieves better constraint satisfaction than baselines while maintaining competitive task performance. The code has been made public.
Report timeline
- MDPO: A Multi-Constraint Policy Optimization Reinforcement Learning Method for Dexterous Manipulation
The authors propose Multi-constraint Dexterous Policy Optimization (MDPO), which formulates dexterous manipulation as a multi-constraint policy optimization problem involving both cumulative cost constraints and state-wise cost constraints, and integrates multi-constraint projection into the policy optimization process. In experiments on ReDMan for safe joint control, finger safety, and grasping tasks, MDPO achieved better constraint satisfaction than baselines while maintaining competitive task performance. The code is publicly available.
arXiv cs.RO ·