arXiv Robotics — research abstracts· Derek You, Zafir Shamsi, Keqin Wang, Christine Allen-Blanchette·· 10 days agoEditorial score19
Higher-Order Morphology Priors for Quadruped Reinforcement Learning
Higher-Order Morphology Priors for Quadruped Reinforcement Learning Under Actuator Degradation
Summary
Study shows higher-order morphology improves quadruped locomotion under actuator degradation. Hodge-based policy outperforms others in survival and tracking accuracy.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
Source：arXiv Robotics — research abstracts · arxiv.org