{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:42:47Z","timestamp":1729640567677,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,12]]},"DOI":"10.1109\/robio.2011.6181717","type":"proceedings-article","created":{"date-parts":[[2012,4,13]],"date-time":"2012-04-13T15:36:46Z","timestamp":1334331406000},"page":"2725-2732","source":"Crossref","is-referenced-by-count":2,"title":["Human-like gradual multi-agent Q-learning using the concept of behavior-based robotics for autonomous exploration"],"prefix":"10.1109","author":[{"given":"Dip N","family":"Ray","sequence":"first","affiliation":[]},{"given":"Amit","family":"Mandal","sequence":"additional","affiliation":[]},{"given":"Somajyoti","family":"Majumder","sequence":"additional","affiliation":[]},{"given":"Sumit","family":"Mukhopadhyay","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511527234.004"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1986.1087032"},{"key":"18","first-page":"991","article-title":"The Dynamics of Action Selection","author":"maes","year":"1989","journal-title":"Proceedings of the International Joint Conference on Artificial Intelligence"},{"key":"15","first-page":"151","article-title":"Multi-agent Control Structure for a Vision Based Robot Soccer System","author":"li","year":"2004","journal-title":"Proceedings of IEEE International Conference on Mechatronics and Machine Vision in Practice Macao China"},{"key":"16","article-title":"Intelligence without reason","author":"brooks","year":"0","journal-title":"Proc of the Conference of International Joint Conference on Artificial Intelligence 1991"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1998.680648"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1080\/10798587.2000.10768155"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00114-2"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"journal-title":"Behavior-Based Robotics","year":"1998","author":"arkin","key":"21"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1177\/027836498900800406"},{"key":"22","article-title":"A Case study in the behavior-oriented design of autonomous agents","author":"steels","year":"1994","journal-title":"Proc of 3rd International Conference on Simulation of Adaptive Behavior"},{"key":"23","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"24"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1017\/S026988890000789X"},{"journal-title":"How Children Learn","year":"0","author":"vosniadou","key":"27"},{"key":"28","first-page":"583","article-title":"A Proposed Methodology for Behaviour-based Multi-Agent Q-learning for Autonomous Exploration","volume":"2","author":"ray","year":"2011","journal-title":"Proc 26th International Conference on CAD\/CAM Robotics and Factories of Future 2011 Kuala Lumpur Malaysia"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041516"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345353"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"10","first-page":"435","article-title":"Karlsruhe Brainstormers - A Reinforcement Learning Approach to RoboticSoccer","author":"merke","year":"2001","journal-title":"Proceedings of RoboCup-2001 USA"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"1"},{"journal-title":"Quicker Q-Learning in Multi-Agent Systems","year":"0","author":"agogino","key":"7"},{"key":"6","first-page":"1167","article-title":"Classes of multiagent Q-learning dynamics with e-greedy exploration","author":"wunder","year":"2010","journal-title":"Proc of International Conference on Machine Learning (ICML 2010) Haifa Israel"},{"journal-title":"Multiagent reinforcement learning Stochastic games with multiple learning players","year":"2003","author":"chalkiadakis","key":"5"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"9","first-page":"355","article-title":"Case-Based Multiagent Reinforcement Learning: Cases as Heuristics for Selection of Actions","author":"bianchi","year":"2010","journal-title":"Proceedings of 19th European Conference on Artificial Intelligence 2010 Portugal"},{"key":"8","first-page":"322","article-title":"Friend-or-Foe Q-learning in General-sum Games","author":"littman","year":"2001","journal-title":"Proceedings of the Eighteenth International Conference on Machine Learning"}],"event":{"name":"2011 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2011,12,7]]},"location":"Karon Beach, Thailand","end":{"date-parts":[[2011,12,11]]}},"container-title":["2011 IEEE International Conference on Robotics and Biomimetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6175417\/6181246\/06181717.pdf?arnumber=6181717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,27]],"date-time":"2019-06-27T04:39:39Z","timestamp":1561610379000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6181717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/robio.2011.6181717","relation":{},"subject":[],"published":{"date-parts":[[2011,12]]}}}