{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:26:41Z","timestamp":1729643201080,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,10]]},"DOI":"10.1109\/iros.2009.5354406","type":"proceedings-article","created":{"date-parts":[[2009,12,18]],"date-time":"2009-12-18T13:17:52Z","timestamp":1261142272000},"page":"1190-1196","source":"Crossref","is-referenced-by-count":7,"title":["Cooperative multi-robot reinforcement learning: A framework in hybrid state space"],"prefix":"10.1109","author":[{"given":"Xueqing","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jerald D.","family":"Kralik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura E.","family":"Ray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"journal-title":"Reinforcement Learning","year":"1998","author":"sutton","key":"17"},{"key":"18","first-page":"279","volume":"8","author":"watkins","year":"1992","journal-title":"Technical Note Q-Learning Machine Learning"},{"key":"15","first-page":"1289","article-title":"Reinforcement learning of cooperative behaviors for multi-robot tracking of multiple moving targets","author":"liu","year":"2005","journal-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"16"},{"key":"13","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00026-0"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273640"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"21","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":"Asynchronous stochastic approximation and Q-learning","year":"1994","author":"tsitsiklis","key":"20"},{"key":"22","article-title":"Principled approaches to the design of multi-robot systems","author":"jones","year":"2004","journal-title":"Proceedings of the Workshop on Networked Robotics IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"23","first-page":"15","article-title":"Engines of the brain: The computational instruction set of human cognition","volume":"27","author":"granger","year":"2006","journal-title":"AI Magazine"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1162\/089892904970690"},{"key":"25","doi-asserted-by":"crossref","first-page":"8462","DOI":"10.1523\/JNEUROSCI.20-22-08462.2000","article-title":"Origins and distribution of cholinergically induced beta rhythms in hippocampal slices","volume":"20","author":"shimono","year":"2000","journal-title":"Journal of Neuroscience"},{"journal-title":"Learning Hierarchical Representations and Behaviors","year":"2008","author":"hearn","key":"26"},{"journal-title":"Vision-Based Perception for Reinforcement Learning in Multi-Robot Systems","year":"2009","author":"nowak","key":"27"},{"key":"28","first-page":"560","author":"duda","year":"2005","journal-title":"Pattern Classification"},{"journal-title":"Introduction to Algorithms","year":"1990","author":"cormen","key":"29"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1242005"},{"key":"2","first-page":"136","article-title":"Collective search by mobile robots using alpha-beta coordination","author":"goldsmith","year":"1998","journal-title":"Conference on Collective Robotics Workshop"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1145\/860685.860689"},{"key":"1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1023\/A:1008819414322","article-title":"Reinforcement Learning in the Multi-Robot Domain","volume":"4","author":"mataric?","year":"1997","journal-title":"Autonomous Robots"},{"key":"30","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/3-540-36478-1_17","article-title":"Exact Algorithms for NP-Hard Problems: A Survey","volume":"2570","author":"woeginger","year":"2003","journal-title":"Lecture Notes in Computer Science"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.4159\/harvard.9780674419131.c7"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.4159\/harvard.9780674419131.c4"},{"journal-title":"Webots Reference Manual Cyberbotics Ltd Professional Mobile Robot Simulation Software","year":"0","key":"32"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651073"},{"key":"31","first-page":"1292","article-title":"Heterogeneous multirobot coordination with spatial and temporal constraints","author":"koes","year":"2005","journal-title":"Proceedings of the Twentieth National Conference on Artificial Intelligence (AAAI-05)"},{"key":"4","article-title":"New criteria and a new algorithm for learning in multi-agent systems","author":"powers","year":"2005","journal-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"9","first-page":"242","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","author":"hu","year":"1998","journal-title":"Proceedings of the Fifteenth International Conference on Machine Learning"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"}],"event":{"name":"2009 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)","start":{"date-parts":[[2009,10,10]]},"location":"St. Louis, MO, USA","end":{"date-parts":[[2009,10,15]]}},"container-title":["2009 IEEE\/RSJ International Conference on Intelligent Robots and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5342790\/5353884\/05354406.pdf?arnumber=5354406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T13:01:07Z","timestamp":1558702867000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5354406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,10]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros.2009.5354406","relation":{},"subject":[],"published":{"date-parts":[[2009,10]]}}}