]> 2026-07-14T13:03:54+00:00 Risk-Averse Planning Under Uncertainty 0 en 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. Mohamadreza Ahmadi Masahiro Ono Michel D. Ingham Richard M. Murray Aaron D. Ames 2019l 2020 American Control Conference (ACC) ahm+20-acc Conference paper 2020-05-26T05:57:43Z 2458995.7484144 Risk-Averse Planning Under Uncertainty Title 102 en Title