Optimizing the expected mean payoff in Energy Markov Decision Processes Conference Paper

Author(s): Brázdil, Tomáš; Kučera, Antonín; Novotný, Petr
Title: Optimizing the expected mean payoff in Energy Markov Decision Processes
Title Series: LNCS
Affiliation IST Austria
Abstract: Energy Markov Decision Processes (EMDPs) are finite-state Markov decision processes where each transition is assigned an integer counter update and a rational payoff. An EMDP configuration is a pair s(n), where s is a control state and n is the current counter value. The configurations are changed by performing transitions in the standard way. We consider the problem of computing a safe strategy (i.e., a strategy that keeps the counter non-negative) which maximizes the expected mean payoff.
Keywords: Markov Decision Processes; Computer science; mean payoff; Artificial intelligence; Non negatives; Finite state; Computers Control state; nocv1
Conference Title: ATVA: Automated Technology for Verification and Analysis
Volume: 9938
Conference Dates: October 17 - 20, 2016
Conference Location: Chiba, Japan
ISBN: 978-3-642-24371-4
Publisher: Springer  
Date Published: 2016-01-01
Start Page: 32
End Page: 49
Sponsor: The research was funded by the Czech Science Foundation Grant No. P202/12/G061 and by the People Programme (Marie Curie Actions) of the European Union’s Seventh Framework Programme (FP7/2007-2013) under REA grant agreement no [291734].
DOI: 10.1007/978-3-319-46520-3_3
Open access: yes (repository)
IST Austria Authors
Related IST Austria Work