学習された制約は実は後方到達可能チューブである
Your Learned Constraint is Secretly a Backward Reachable Tube
逆制約学習(ICL)が理論的・実践的に何を復元するかを解析し、失敗集合ではなく失敗が不可避な状態集合(後方到達可能チューブ)を復元することを示した論文。
著者: Mohamad Qadri, Gokul Swamy, Jonathan Francis, Michael Kaess, Andrea Bajcsy
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Inverse Constraint Learning (ICL) is the problem of inferring constraints from safe (i.e., constraint-satisfying) demonstrations. The hope is that these inferred constraints can then be used downstream to search for safe policies for new tasks and, potentially, under different dynamics. Our paper explores the question of what mathematical entity ICL recovers. Somewhat surprisingly, we show that both in theory and in practice, ICL recovers the set of states where failure is inevitable, rather than the set of states where failure has already happened. In the language of safe control, this means we recover a backwards reachable tube (BRT) rather than a failure set. In contrast to the failure set, the BRT depends on the dynamics of the data collection system. We discuss the implications of the dynamics-conditionedness of the recovered constraint on both the sample-efficiency of policy search and the transferability of learned constraints.
