no code implementations • 9 Sep 2021 • Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray, Aaron D. Ames
In this paper, we consider the problem of designing policies for MDPs and POMDPs with objectives and constraints in terms of dynamic coherent risk measures, which we refer to as the constrained risk-averse problem.
no code implementations • 4 Dec 2020 • Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray, Aaron D. Ames
We consider the problem of designing policies for Markov decision processes (MDPs) with dynamic coherent risk objectives and constraints.
no code implementations • 5 Feb 2020 • Mohamadreza Ahmadi, Arun A. Viswanathan, Michel D. Ingham, Kymie Tan, Aaron D. Ames
Technology development efforts in autonomy and cyber-defense have been evolving independently of each other, over the past decade.
no code implementations • 27 Sep 2019 • Mohamadreza Ahmadi, Masahiro Ono, Michel D. Ingham, Richard M. Murray, Aaron D. Ames
We consider the problem of designing policies for partially observable Markov decision processes (POMDPs) with dynamic coherent risk objectives.