@InProceedings{kretinsky_et_al:LIPIcs.CONCUR.2018.8,
  author =	{Kret{\'\i}nsk\'{y}, Jan and P\'{e}rez, Guillermo A. and Raskin, Jean-Fran\c{c}ois},
  title =	{{Learning-Based Mean-Payoff Optimization in an Unknown MDP under Omega-Regular Constraints}},
  booktitle =	{29th International Conference on Concurrency Theory (CONCUR 2018)},
  pages =	{8:1--8:18},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-087-3},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{118},
  editor =	{Schewe, Sven and Zhang, Lijun},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CONCUR.2018.8},
  URN =		{urn:nbn:de:0030-drops-95468},
  doi =		{10.4230/LIPIcs.CONCUR.2018.8},
  annote =	{Keywords: Markov decision processes, Reinforcement learning, Beyond worst case}
}