Risk-Averse Planning Under Uncertainty
Robotics
2019-09-30 v1 Artificial Intelligence
Optimization and Control
Abstract
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.
Cite
@article{arxiv.1909.12499,
title = {Risk-Averse Planning Under Uncertainty},
author = {Mohamadreza Ahmadi and Masahiro Ono and Michel D. Ingham and Richard M. Murray and Aaron D. Ames},
journal= {arXiv preprint arXiv:1909.12499},
year = {2019}
}