Reinforcement learning in multidimensional continuous action spacesReinforcement learning in multidimensional continuous action spaces Μεταπτυχιακή Διατριβή 2014-03-242012enΜη διαθέσιμοhttp://creativecommons.org/licenses/by/3.0/Reinforcement learning in multidimensional continuous action spacesChania [Greece]Library of TUC2014-03-24application/pdfhttp://www.library.tuc.gr/artemis/MT2012-0109/MT2012-0109.pdffree Πάζης Ιάσων Λαγουδάκης Μιχαήλ Πολυτεχνείο Κρήτης Reinforcement learning (Machine learning) Markov processes