マルチロボット計画の聖杯：オフライン最適専門家からオンライン拡張可能な解を学習する
The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts
小規模系の最適解を学習して大規模マルチロボット計画へ転移するアイデアの課題を整理し、今後の研究方向を論じたブルースカイ論文。
著者: Amanda Prorok, Jan Blumenkamp, Qingbiao Li, Ryan Kortvelesy, Zhe Liu, Ethan Stump
分類: cs.RO, cs.LG, cs.MA
原文アブストラクト
Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances. The use of learning-based methods in multi-robot planning holds great promise as it enables us to offload the online computational burden of expensive, yet optimal solvers, to an offline learning procedure. Simply put, the idea is to train a policy to copy an optimal pattern generated by a small-scale system, and then transfer that policy to much larger systems, in the hope that the learned strategy scales, while maintaining near-optimal performance. Yet, a number of issues impede us from leveraging this idea to its full potential. This blue-sky paper elaborates some of the key challenges that remain.
