An Approximate Solution Method for Large Risk-Averse Markov Decision Processes
Portfolio Management
2012-10-19 v1 Artificial Intelligence
Computer Science and Game Theory
Abstract
Stochastic domains often involve risk-averse decision makers. While recent work has focused on how to model risk in Markov decision processes using risk measures, it has not addressed the problem of solving large risk-averse formulations. In this paper, we propose and analyze a new method for solving large risk-averse MDPs with hybrid continuous-discrete state spaces and continuous action spaces. The proposed method iteratively improves a bound on the value function using a linearity structure of the MDP. We demonstrate the utility and properties of the method on a portfolio optimization problem.
Keywords
Cite
@article{arxiv.1210.4901,
title = {An Approximate Solution Method for Large Risk-Averse Markov Decision Processes},
author = {Marek Petrik and Dharmashankar Subramanian},
journal= {arXiv preprint arXiv:1210.4901},
year = {2012}
}
Comments
Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)