不確実性下におけるリスク回避型計画法
Risk-Averse Planning Under Uncertainty
動的リスク指標を持つPOMDPに対し、有限メモリの確率的制御器を凸最適化で設計する有界方策反復法を提案した論文。
著者: Mohamadreza Ahmadi, Masahiro Ono, Michel D. Ingham, Richard M. Murray, Aaron D. Ames
分類: cs.RO, cs.AI, math.OC
原文アブストラクト
We consider the problem of designing policies for partially observable Markov decision processes (POMDPs) with dynamic coherent risk objectives. Synthesizing risk-averse optimal policies for POMDPs requires infinite memory and thus undecidable. To overcome this difficulty, we propose a method based on bounded policy iteration for designing stochastic but finite state (memory) controllers, which takes advantage of standard convex optimization methods. Given a memory budget and optimality criterion, the proposed method modifies the stochastic finite state controller leading to sub-optimal solutions with lower coherent risk.
