Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1306804,
author = {Chatterjee, Krishnendu and Komárková, Zuzana and Křetínský, Jan},
address = {Los Alamitos, California},
booktitle = {Thirtieth Annual ACM/IEEE Symposium on Logic in Computer Science (LICS)},
doi = {http://dx.doi.org/10.1109/LICS.2015.32},
keywords = {Markov decision process; mean payoff; optimization; probability},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Los Alamitos, California},
isbn = {978-1-4799-8875-4},
pages = {244-256},
publisher = {IEEE},
title = {Unifying Two Views on Multiple Mean-Payoff Objectives in Markov Decision Processes},
year = {2015}
}
TY - JOUR
ID - 1306804
AU - Chatterjee, Krishnendu - Komárková, Zuzana - Křetínský, Jan
PY - 2015
TI - Unifying Two Views on Multiple Mean-Payoff Objectives in Markov Decision Processes
PB - IEEE
CY - Los Alamitos, California
SN - 9781479988754
KW - Markov decision process
KW - mean payoff
KW - optimization
KW - probability
N2 - We consider Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) objectives. There exist two different views: (i)~the expectation semantics, where the goal is to optimize the expected mean-payoff objective, and (ii)~the satisfaction semantics, where the goal is to maximize the probability of runs such that the mean-payoff value stays above a given vector. We consider optimization with respect to both objectives at once, thus unifying the existing semantics. Precisely, the goal is to optimize the expectation while ensuring the satisfaction constraint. Our problem captures the notion of optimization with respect to strategies that are risk-averse (i.e., ensure certain probabilistic guarantee). Our main results are as follows: First, we present algorithms for the decision problems, which are always polynomial in the size of the MDP. We also show that an approximation of the Pareto curve can be computed in time polynomial in the size of the MDP, and the approximation factor, but exponential in the number of dimensions. Second, we present a complete characterization of the strategy complexity (in terms of memory bounds and randomization) required to solve our problem.
ER -
CHATTERJEE, Krishnendu, Zuzana KOMÁRKOVÁ and Jan KŘETÍNSKÝ. Unifying Two Views on Multiple Mean-Payoff Objectives in Markov Decision Processes. In \textit{Thirtieth Annual ACM/IEEE Symposium on Logic in Computer Science (LICS)}. Los Alamitos, California: IEEE, 2015, p.~244-256. ISBN~978-1-4799-8875-4. Available from: https://dx.doi.org/10.1109/LICS.2015.32.
|
