Conditional Value-at-Risk for Reachability and Mean Payoff in Markov Decision Processes
Logic in Computer Science
2018-05-09 v1
Abstract
We present the conditional value-at-risk (CVaR) in the context of Markov chains and Markov decision processes with reachability and mean-payoff objectives. CVaR quantifies risk by means of the expectation of the worst p-quantile. As such it can be used to design risk-averse systems. We consider not only CVaR constraints, but also introduce their conjunction with expectation constraints and quantile constraints (value-at-risk, VaR). We derive lower and upper bounds on the computational complexity of the respective decision problems and characterize the structure of the strategies in terms of memory and randomization.
Keywords
Cite
@article{arxiv.1805.02946,
title = {Conditional Value-at-Risk for Reachability and Mean Payoff in Markov Decision Processes},
author = {Jan Křetínský and Tobias Meggendorfer},
journal= {arXiv preprint arXiv:1805.02946},
year = {2018}
}