{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T04:12:00Z","timestamp":1685419920586},"reference-count":0,"publisher":"National Library of Serbia","issue":"3","license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ComSIS","COMPUT SCI INF SYST","COMPUT SCI INFORM SY","COMPUTER SCI INFORM","COMSIS J"],"published-print":{"date-parts":[[2017]]},"abstract":"<jats:p>Reinforcement learning is an efficient learning method for the control\n   problem by interacting with the environment to get an optimal policy.\n   However, it al so faces challenges such as low convergence accuracy and slow\n   convergence. More over, conventional reinforcement learning algorithms could\n   hardly solve continuous control problems. The kernel-based method can\n   accelerate convergence speed and improve convergence accuracy; and the\n   policy gradient method is a good way to deal with continuous space\n   problems. We proposed a Sarsa(?) version of true online time difference\n   algorithm, named True Online Sarsa(?)(TOSarsa(?)), on the basis of the\n   clustering-based sample specification method and selective kernel-based\n   value function. The TOSarsa(?) algorithm has a consistent result with both\n   the forward view and the backward view which ensures to get an optimal\n   policy in less time. Afterwards we also combined TOSarsa(?) with heuristic\n   dynamic programming. The experiments showed our proposed algorithm worked\n   well in dealing with continuous control problem.<\/jats:p>","DOI":"10.2298\/csis170107029z","type":"journal-article","created":{"date-parts":[[2017,9,20]],"date-time":"2017-09-20T10:30:00Z","timestamp":1505903400000},"page":"789-804","source":"Crossref","is-referenced-by-count":2,"title":["A kernel based true online Sarsa(\u03bb) for continuous space control problems"],"prefix":"10.2298","volume":"14","author":[{"given":"Fei","family":"Zhu","sequence":"first","affiliation":[{"name":"Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China + Soochow University, Provincial Key Laboratory for Computer Information Processing Technology, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haijun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Changshu Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Soochow University, School of Computer Science and Technology, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoke","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Basque Country, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1078","container-title":["Computer Science and Information Systems"],"original-title":[],"language":"en","deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T08:33:11Z","timestamp":1685349191000},"score":1,"resource":{"primary":{"URL":"https:\/\/doiserbia.nb.rs\/Article.aspx?ID=1820-02141700029Z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":0,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017]]}},"URL":"https:\/\/doi.org\/10.2298\/csis170107029z","relation":{},"ISSN":["1820-0214","2406-1018"],"issn-type":[{"value":"1820-0214","type":"print"},{"value":"2406-1018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}