{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T02:52:45Z","timestamp":1719975165215},"reference-count":13,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2017]]},"DOI":"10.1587\/transinf.2017edl8112","type":"journal-article","created":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T22:19:47Z","timestamp":1509488387000},"page":"2721-2724","source":"Crossref","is-referenced-by-count":3,"title":["A Study of Qualitative Knowledge-Based Exploration for Continuous Deep Reinforcement Learning"],"prefix":"10.1587","volume":"E100.D","author":[{"given":"Chenxi","family":"LI","sequence":"first","affiliation":[{"name":"Institute of Command Information System, PLA University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"CAO","sequence":"additional","affiliation":[{"name":"Institute of Command Information System, PLA University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"LIU","sequence":"additional","affiliation":[{"name":"Institute of Command Information System, PLA University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiliang","family":"CHEN","sequence":"additional","affiliation":[{"name":"Institute of Command Information System, PLA University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixiong","family":"XU","sequence":"additional","affiliation":[{"name":"Institute of Command Information System, PLA University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongliang","family":"ZHANG","sequence":"additional","affiliation":[{"name":"Institute of Command Information System, PLA University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] R. Sutton and A. Barto, Reinforcement Learning: An Introduc-tion, MIT Press, 1998.","DOI":"10.1109\/TNN.1998.712192"},{"key":"2","unstructured":"[2] L.A. Celiberto, J.P. Matsuura, R.L.D. Mantaras, and R.A.C. Bianchi, Using Cases as Heuristics in Reinforcement Learning: A Transfer Learning Application, IJCAI, pp.1211-1217, 2011."},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] R.A.C. Bianchi, L.A. Celiberto, P.E. Santos, J.P. Matsuura, and R.L. de Mantaras, Transferring knowledge as heuristics in reinforcement learning: A case-based approach, Artificial Intelligence, vol.226, pp.102-121, 2015. 10.1016\/j.artint.2015.05.008","DOI":"10.1016\/j.artint.2015.05.008"},{"key":"4","unstructured":"[4] R.A.C. Bianchi, C.H.C. Ribeiro, and A.H.R. Costa, Heuristically Accelerated Reinforcement Learning: Theoretical and Experimental Results, Frontiers in Artificial Intelligence & Applications, p.242, 2012."},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] M. Santos, J.A. Mart\u00edn H, V. L\u00f3pez, and G. Botella, Dyna-H: A heuristic planning reinforcement learning algorithm applied to role-playing game strategy decision systems, Knowledge-Based Systems, vol.32, no.8, pp.28-36, 2012. 10.1016\/j.knosys.2011.09.008","DOI":"10.1016\/j.knosys.2011.09.008"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] K. Miyazaki, M. Yamamura, and S. Kobayashi, k-Certainty Exploration Method: an action selector to identify the environment in reinforcement learning, Artificial Intelligence, vol.91, no.1, pp.155-171, 1997. 10.1016\/s0004-3702(96)00062-8","DOI":"10.1016\/S0004-3702(96)00062-8"},{"key":"7","unstructured":"[7] G. Kuhlmann, P. Stone, R. Mooney, and J. Shavlik, Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer, The AAAI-2004 workshop on supervisory control of learning and adaptive systems, 2004."},{"key":"8","unstructured":"[8] D.L. Moreno, C.V. Regueiro, R. Iglesias, and S. Barro, Using prior knowledge to improve reinforcement learning in mobile robotics, Proc. Towards Autonomous Robotics Systems. Univ. of Essex, UK, 2004."},{"key":"9","unstructured":"[9] G. Brockman, V. Cheung, L. Pettersson, J. Schneider, J. Schulman, J. Tang, and W. Zaremba, OpenAI Gym., arXiv preprint arXiv: 1606.01540, 2016."},{"key":"10","unstructured":"[10] L.X. Wang, A Course in Fuzzy Systems and Control, Prentice Hall, 1997."},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] D. Li, D. Cheung, X. Shi, and V. Ng, Uncertainty reasoning based on cloud models in controllers, Computers & Mathematics with Applications, vol.35, no.3, pp.99-123, 1998. 10.1016\/s0898-1221(97)00282-4","DOI":"10.1016\/S0898-1221(97)00282-4"},{"key":"12","unstructured":"[12] D.Y Li and Y. Du. Artificial Intelligence with Uncertainty, National Defense Industry Press, Beijing, May 2014."},{"key":"13","unstructured":"[13] T.P. Lillicrap, J.J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra, Continuous control with deep reinforcement learning, arXiv preprint arXiv:1509.02971, 2015."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/11\/E100.D_2017EDL8112\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,5]],"date-time":"2019-10-05T11:56:10Z","timestamp":1570276570000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/11\/E100.D_2017EDL8112\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":13,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2017]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2017edl8112","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}