@inproceedings{1326, 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. }, author = {Brázdil, Tomáš and Kučera, Antonín and Novotny, Petr}, location = {Chiba, Japan}, pages = {32 -- 49}, publisher = {Springer}, title = {{Optimizing the expected mean payoff in Energy Markov Decision Processes}}, doi = {10.1007/978-3-319-46520-3_3}, volume = {9938}, year = {2016}, }