{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T01:29:48Z","timestamp":1729646988553,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,10]]},"DOI":"10.1109\/iros.2010.5652923","type":"proceedings-article","created":{"date-parts":[[2010,12,10]],"date-time":"2010-12-10T21:37:26Z","timestamp":1292017046000},"page":"3244-3250","source":"Crossref","is-referenced-by-count":2,"title":["Socially augmented hierarchical reinforcement learning for reducing complexity in cooperative multi-agent systems"],"prefix":"10.1109","author":[{"family":"Xueqing Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L E","family":"Ray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J D","family":"Kralik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Dongqing Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1098\/rstb.2006.1997"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.4159\/harvard.9780674419131.c7"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1086\/233874"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1126\/science.1140734"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1613\/jair.1427","article-title":"Decentralized control of cooperative systems: Categorization and complexity analysis","volume":"22","author":"goldman","year":"2004","journal-title":"Journal of Artificial Intelligence Research"},{"year":"2009","author":"sanjeev","article-title":"Complexity Theory: A Modern Approach","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1007\/BF00992698"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1162\/neco.1994.6.6.1185"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/BF00993306"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TSMCC.2007.913919"},{"year":"1998","author":"sutton","journal-title":"Reinforcement Learning","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/s10458-006-7035-4"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref8","first-page":"195","article-title":"Planning, learning and coordination in multi-agent decision processes","author":"boutilier","year":"1996","journal-title":"Proceedings 6th Conference on Theoretical Aspects of Rationality and Knowledge (TARK-96) De Zeeuwse Stromen The Netherlands"},{"key":"ref7","first-page":"276","article-title":"On the synthesis of useful social laws for artificial agent societies","author":"shoham","year":"1992","journal-title":"Proceedings of the Tenth National Conference on Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1145\/860575.860816"},{"key":"ref9","article-title":"High level coordination of agents based on multi-agent Markov decision processes with roles","author":"spaan","year":"2002","journal-title":"Workshop on Cooperative Robotics IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref20","first-page":"746","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 AAAI Press"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICMAS.1998.699055"},{"key":"ref21","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proceedings of the 11th International Conference of Machine Learning (ICML) Morgan Kaufmann"},{"key":"ref24","article-title":"Role Selection in Multi-Robot Systems using Abstract State-Based Reinforcement Learning","author":"mao","year":"2009","journal-title":"the Proceedings of the 14th IASTED International Conference on Robotics and Applications"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/IROS.2009.5354406"},{"year":"0","journal-title":"Webots Reference Manual[M]","article-title":"Cyberbotics Ltd. Professional Mobile Robot Simulation Software","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.2307\/1929145"}],"event":{"name":"2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2010)","start":{"date-parts":[[2010,10,18]]},"location":"Taipei","end":{"date-parts":[[2010,10,22]]}},"container-title":["2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5639431\/5648787\/05652923.pdf?arnumber=5652923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,6]],"date-time":"2019-06-06T20:59:50Z","timestamp":1559854790000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5652923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros.2010.5652923","relation":{},"subject":[],"published":{"date-parts":[[2010,10]]}}}