Publication
Title
Learning-based mean-payoff optimization in an unknown MDP under omega-regular constraints
Author
Abstract
We formalize the problem of maximizing the mean-payoff value with high probability while satisfying a parity objective in a Markov decision process (MDP) with unknown probabilistic transition function and unknown reward function. Assuming the support of the unknown transition function and a lower bound on the minimal transition probability are known in advance, we show that in MDPs consisting of a single end component, two combinations of guarantees on the parity and mean-payoff objectives can be achieved depending on how much memory one is willing to use. (i) For all epsilon and gamma we can construct an online-learning finite-memory strategy that almost-surely satisfies the parity objective and which achieves an epsilon-optimal mean payoff with probability at least 1 - gamma. (ii) Alternatively, for all epsilon and gamma there exists an online-learning infinite-memory strategy that satisfies the parity objective surely and which achieves an epsilon-optimal mean payoff with probability at least 1 - gamma. We extend the above results to MDPs consisting of more than one end component in a natural way. Finally, we show that the aforementioned guarantees are tight, i.e. there are MDPs for which stronger combinations of the guarantees cannot be ensured.
Language
English
Source (journal)
LIPIcs : Leibniz International Proceedings in Informatics. - Place of publication unknown
Source (book)
29th International Conference on Concurrency Theory (CONCUR 2018) / Schewe, Sven [edit.]; et al.
Publication
Germany : Schloss Dagstuhl, Leibniz-Zentrum fuer Informatik , 2018
ISBN
978-3-95977-087-3
Volume/pages
118 (2018) , 18 p.
Article Reference
8
Medium
E-only publicatie
Full text (Publisher's DOI)
Full text (open access)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
External links
Record
Identification
Creation 19.11.2018
Last edited 12.10.2020