{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:05:30Z","timestamp":1729663530242,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/robio.2010.5723346","type":"proceedings-article","created":{"date-parts":[[2011,3,5]],"date-time":"2011-03-05T07:53:28Z","timestamp":1299311608000},"page":"312-319","source":"Crossref","is-referenced-by-count":2,"title":["Fuzzy rule based neuro-dynamic programming for mobile robot skill acquisition on the basis of a nested multi-agent architecture"],"prefix":"10.1109","author":[{"given":"John N.","family":"Karigiannis","sequence":"first","affiliation":[]},{"given":"Theodoros I.","family":"Rekatsinas","sequence":"additional","affiliation":[]},{"given":"Costas S.","family":"Tzafestas","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Webots TM Professional Mobile Robot Simulation","year":"2004","key":"ref31"},{"key":"ref30","article-title":"Replacing Eligibility Trace for action-value Learning with Function Approximation","author":"framling","year":"2007","journal-title":"Proceedings of the 15th European Symposium on Artificial Neural Networks"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281729"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88309-8_39"},{"key":"ref12","article-title":"Temporal Difference Learning in Continuous Time and Space","volume":"8","author":"doya","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2003.11.006"},{"key":"ref14","first-page":"102","article-title":"Application of Direct-Vision-Based Reinforcement Learning to a Real Mobile Robot","volume":"7","author":"masaru","year":"2004","journal-title":"Artificial Life and Robotics"},{"key":"ref15","first-page":"562","article-title":"Fast and Stable Learning in Direct-Vision-Based Reinforcement Learning","author":"shibata","year":"2001","journal-title":"Proc of Intl Sympo On Artificial Life and Robotics (AROB) 6th"},{"article-title":"Learning from Delayed Rewards","year":"1989","author":"watkins","key":"ref16"},{"key":"ref17","first-page":"226243","article-title":"Cooperative mobile robots: Antecedents and directions","volume":"1","author":"cao","year":"1995","journal-title":"Proc IEEE\/RSJ Int Conf Intelligent Robots and Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1996.570849"},{"journal-title":"Advanced Robotics Redundancy and Optimization","year":"1990","author":"nakamura","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2008.4762862"},{"key":"ref4","article-title":"The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems","author":"claus","year":"1998","journal-title":"15th national Conference on Artificial intelligence\/Innovative applications of artificial intelligence AAAI 98\/IAAI 98"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/09540090310001655110"},{"journal-title":"Theoretical Neuroscience Computational and Mathematical Modeling of Neural Systems","year":"2001","author":"dayan","key":"ref3"},{"key":"ref6","article-title":"Sparse Tabular Multiagent Q-Learning","author":"kok","year":"2004","journal-title":"Proceedings of Annual Machine Learning Conference of Benelearn"},{"key":"ref29","article-title":"Multi-agent Architecture with Continuous RL in Fuzzy State-Space for Robot Manipulation Control","author":"karigiannis","year":"2005","journal-title":"International Mediterranean Modeling MultiConference - I3M 2005 IMAACA 2005"},{"key":"ref5","article-title":"Coordinated Reinforcement Learning","author":"guestrin","year":"2002","journal-title":"Proceedings of 19th International Conference on Machine Learning 2002"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/s004220050351","article-title":"Specialization in multi-agent systems through learning","volume":"76","author":"zamora","year":"1997","journal-title":"Biological Cybernetics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1979.10"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref2"},{"key":"ref9","article-title":"Self-Organization of Place Cells and Reward-Based Navigation for a mobile Robot","author":"takahashi","year":"0","journal-title":"ICONIP 2001"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/027836499301200302"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/PL00014414"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/70.928561"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1986.1087032"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/027836499701600506"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49720-2_6"}],"event":{"name":"2010 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2010,12,14]]},"location":"Tianjin, China","end":{"date-parts":[[2010,12,18]]}},"container-title":["2010 IEEE International Conference on Robotics and Biomimetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5720496\/5723286\/05723346.pdf?arnumber=5723346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T16:31:42Z","timestamp":1497889902000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5723346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/robio.2010.5723346","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}