{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:31:06Z","timestamp":1729636266031,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1109\/icarcv.2016.7838691","type":"proceedings-article","created":{"date-parts":[[2017,2,7]],"date-time":"2017-02-07T21:25:47Z","timestamp":1486502747000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Integrating symmetry of environment by designing special basis functions for value function approximation in reinforcement learning"],"prefix":"10.1109","author":[{"given":"Guo-fang","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhou","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref11","first-page":"833","article-title":"Reinforcement learning in continuous action spaces through sequential Monte Carlo methods","volume":"20","author":"bonarini","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","article-title":"Integrating reinforcement learning with human demonstrations of varying ability","author":"taylor","year":"2011","journal-title":"AAMAS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.08.039"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref15","article-title":"Theory and application of reward shaping in reinforcement learning","author":"laud","year":"2004","journal-title":"University of Illinois at Urbana-Champaign"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.01.004"},{"key":"ref17","article-title":"Symmetry in Markov decision processes and its implications for single agent and multi agent learning","author":"zinkevich","year":"2001","journal-title":"Proceedings of the 18th International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.41"},{"key":"ref19","article-title":"Exploiting generalisation symmetries in accuracy-based learning classifier systems: An initial study","author":"bull","year":"2014","journal-title":"arXiv preprint arXiv 1401 2949"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","article-title":"Efficient reinforcement learning using recursive least-squares methods","volume":"16","author":"xu","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref6","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74024-7_9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530856"},{"key":"ref2","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","volume":"19","author":"abbeel","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.08.037"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.03.029"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-0859-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143906"},{"key":"ref21","first-page":"1333","article-title":"Transfer in Reinforcement Learning via Shared Features","volume":"13","author":"konidaris","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.07.008"}],"event":{"name":"2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)","start":{"date-parts":[[2016,11,13]]},"location":"Phuket, Thailand","end":{"date-parts":[[2016,11,15]]}},"container-title":["2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7823366\/7838559\/07838691.pdf?arnumber=7838691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T11:16:12Z","timestamp":1568805372000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7838691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icarcv.2016.7838691","relation":{},"subject":[],"published":{"date-parts":[[2016,11]]}}}