連続観測空間POMDPにおける疎な木探索の最適性保証
Sparse tree search optimality guarantees in POMDPs with continuous observation spaces
連続状態・観測空間を持つPOMDPに対し、観測尤度で重み付けするオンラインサンプリング手法の理論的正当性を証明し、計算資源を増やせば最適解に任意に近づけることを示した。
著者: Michael H. Lim, Claire J. Tomlin, Zachary N. Sunberg
分類: cs.LG, cs.RO, cs.SY, eess.SY, stat.ML
原文アブストラクト
Partially observable Markov decision processes (POMDPs) with continuous state and observation spaces have powerful flexibility for representing real-world decision and control problems but are notoriously difficult to solve. Recent online sampling-based algorithms that use observation likelihood weighting have shown unprecedented effectiveness in domains with continuous observation spaces. However there has been no formal theoretical justification for this technique. This work offers such a justification, proving that a simplified algorithm, partially observable weighted sparse sampling (POWSS), will estimate Q-values accurately with high probability and can be made to perform arbitrarily near the optimal solution by increasing computational power.
