2019/09/27 by Ahmadi, Mohamadreza, Ono, Masahiro, Ingham, Michel D. +2
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #Optimization and Control (math.OC) #Robotics (cs.RO)
paper · doi:10.48550/arxiv.1909.12499
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.