{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:39:45Z","timestamp":1730209185813,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,10]]},"DOI":"10.1109\/coginfocom.2015.7390652","type":"proceedings-article","created":{"date-parts":[[2016,1,28]],"date-time":"2016-01-28T21:42:25Z","timestamp":1454017345000},"page":"545-550","source":"Crossref","is-referenced-by-count":4,"title":["Q-learning vs. FRIQ-learning in the Maze problem"],"prefix":"10.1109","author":[{"given":"Tamas","family":"Tompa","sequence":"first","affiliation":[]},{"given":"Szilveszter","family":"Kovacs","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-34783-6_48"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45493-4_71"},{"key":"ref12","first-page":"531","article-title":"Gradient based parameter optimisation of FRI “FIVE","author":"krizs\u00e1n","year":"0","journal-title":"Proceedings of the 9th International Symposium of Hungarian Researchers on Computational Intelligence and Informatics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"journal-title":"FRIQ-learning framework in the Matlab","year":"2015","author":"vincze","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15220-7_16"},{"key":"ref16","first-page":"533","article-title":"Reduced Rule Base in Fuzzy Rule Interpolation-based Q-learning","author":"vincze","year":"2009","journal-title":"Proceedings of the 10th International Symposium of Hungarian Researchers on Computational Intelligence and Informatics CINTI 2009"},{"key":"ref17","article-title":"Rule-Base Reduction in Fuzzy Rule Interpolation-Based Q-Learning","volume":"2","author":"vincze","year":"2015","journal-title":"Recent Innovations in Mechatronics (RIiM)"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref18"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2004.836085"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1996.553542"},{"article-title":"Q-learing framework and examples in the Matlab","year":"2015","author":"jose antonio","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1996.551807"},{"key":"ref2","first-page":"67","article-title":"Definition and Synergies of Cognitive Infocommunications","volume":"9","author":"baranyi","year":"2012","journal-title":"Acta Polytechnica Hungarica"},{"journal-title":"Model-based Reinforcement Learning in Continuous Environments","year":"2000","author":"appl","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0165-0114(94)90311-5"}],"event":{"name":"2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)","start":{"date-parts":[[2015,10,19]]},"location":"Gyor","end":{"date-parts":[[2015,10,21]]}},"container-title":["2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7369419\/7390553\/07390652.pdf?arnumber=7390652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T23:03:51Z","timestamp":1490396631000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7390652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/coginfocom.2015.7390652","relation":{},"subject":[],"published":{"date-parts":[[2015,10]]}}}