{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T03:45:25Z","timestamp":1760586325484},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2005,5,1]],"date-time":"2005-05-01T00:00:00Z","timestamp":1114905600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2005,5]]},"DOI":"10.1007\/s10458-004-4344-3","type":"journal-article","created":{"date-parts":[[2005,2,28]],"date-time":"2005-02-28T19:41:33Z","timestamp":1109619693000},"page":"273-328","source":"Crossref","is-referenced-by-count":12,"title":["Coordinating Multiple Agents via Reinforcement Learning"],"prefix":"10.1007","volume":"10","author":[{"given":"Gang","family":"Chen","sequence":"first","affiliation":[]},{"given":"Zhonghua","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"He","sequence":"additional","affiliation":[]},{"given":"Kiah Mok","family":"Goh","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"4","key":"CR1","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/5326.897075","volume":"30","author":"O. Abul","year":"2000","journal-title":"IEEE Trans. Syst., Man, Cyber"},{"key":"CR2","doi-asserted-by":"crossref","unstructured":"S. Arai, K. Sycara, and T. R. Payne, ??Multi-agent reinforcement learning for scheduling multiple-goals??, in Proceedings of the fourth International Conference on Multi-Agent Systems, 2000.","DOI":"10.1109\/ICMAS.2000.858474"},{"key":"CR3","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957a"},{"key":"CR4","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957b"},{"key":"CR5","doi-asserted-by":"crossref","unstructured":"H. R. Berenji and D. Vengerov, ??Cooperation and coordination between fuzzy reinforcement learning agents in continuous state partially observable Markov decision processes??, in Proceedings of the 8th IEEE International Conference on Fuzzy Systems, 1999. pp. 621-627.","DOI":"10.1109\/FUZZY.1999.793014"},{"key":"CR6","volume-title":"Dynamic Programming","author":"D. P. Bertsekas","year":"1987"},{"key":"CR7","unstructured":"D. P. Bertsekas and J. N. Tsitsiklis, Neuro-Dynamic Programming, Athena Scientific, 1996."},{"key":"CR8","doi-asserted-by":"crossref","unstructured":"A. Bonarini and V. Trianni, ??Learning fuzzy classifier systems for multi-agent coordination??, Int. J. of Inform. Sci. pp. 215-239, 2001.","DOI":"10.1016\/S0020-0255(01)00149-9"},{"key":"CR9","volume-title":"Readings in Distributed Artificial Intelligence","year":"1988"},{"key":"CR10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.575","volume":"Vol. 11","author":"C. Boutilier","year":"1999","journal-title":"J. Artif. Intelligence Res."},{"key":"CR11","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/S0004-3702(00)00033-3","volume":"Vol. 121","author":"C. Boutilier","year":"2000","journal-title":"Artif. Intell."},{"key":"CR12","volume-title":"Intelligent Systems and Interfaces","author":"H. Bunke","year":"2000"},{"key":"CR13","doi-asserted-by":"crossref","unstructured":"G. Chalkiadakis and C. Boutilier, ??Coordination in multiagent reinforcement learning: A bayesian approach??, in Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-03). Melbourne, Australia, 2003, pp. 709?716.","DOI":"10.1145\/860575.860689"},{"key":"CR14","doi-asserted-by":"crossref","unstructured":"G. Chen, Z. Yang, H. He, and K. M. Goh, ??A fuzzy logic based multiagent coordination framewrok??, in Proceedings of the International Conference on Intelligent Agents, Web Technologies and Internet Commerce, 2003, Vienna, Austria.","DOI":"10.1145\/860575.860745"},{"key":"CR15","volume-title":"Stochastic approximation and its Applications","author":"H. Chen","year":"2002"},{"key":"CR16","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1007518724497","volume":"33","author":"R. H. Crites","year":"1998","journal-title":"Machine Learning"},{"key":"CR17","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/S0004-3702(96)00023-9","volume":"89","author":"R. Dearden","year":"1997","journal-title":"Artif. Intell."},{"key":"CR18","unstructured":"K. S. Decker ??Environment centered analysis and design of coordination mechanisms??, Ph.D. thesis, University of Massachusetts Amherst, 1995."},{"key":"CR19","doi-asserted-by":"crossref","unstructured":"K. S. Decker and V. R. Lesser, ??Generalizing the partial global planning algorithm??, Int. J. Intell. Cooperative Inform. Syst., pp. 319?346, 1992.","DOI":"10.1142\/S0218215792000222"},{"key":"CR20","volume-title":"??Coordination of Distributed Problem Solvers??","year":"1988"},{"key":"CR21","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/B978-1-55860-092-8.50014-9","volume":"vol. 2","author":"E. H. Durfee","year":"1989","journal-title":"Distributed Artificial Intelligence"},{"key":"CR22","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/S0004-3702(02)00376-4","volume":"vol. 147","author":"R. Givan","year":"2003","journal-title":"Artif. Intell."},{"key":"CR23","volume-title":"??Context specific multiagent coordination and planning with factored MDPs??, in AAAI Spring Symposium on Collaborative Learning Agents","author":"C. Guestrin","year":"2002"},{"key":"CR24","doi-asserted-by":"crossref","unstructured":"M. Heger, ??Consideration of risk in reinforcement learning??, in Proceedings of the 11th International Conference on Machine Learning, 1994. pp. 105?111.","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"key":"CR25","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511810817","volume-title":"Matrix Analysis","author":"R. A. Horn","year":"1985"},{"key":"CR26","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"vol. 4","author":"L. P. Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"CR27","unstructured":"S. Kapetanakis and D. Kudenko, ??Reinforcement learning of coordination in cooperative multi-agent systems??, in Eighteenth National Conference on Artificial Intelligence, 2002. Edmonton, Alberta, Canada, pp. 326?331."},{"key":"CR28","doi-asserted-by":"crossref","unstructured":"T. W. Malone and K. Crowston, ??What is coordination theory and how can it help design cooperative work systems???, in Proceedings of the 1990 ACM conference on Computer-Supported Cooperative Work, 1990. pp. 357?370.","DOI":"10.1145\/99332.99367"},{"key":"CR29","doi-asserted-by":"crossref","unstructured":"M. L. Puterman, ??Markov decision processes,?? in D. P. Heyman and M. J. Sobel (eds.), Handbook in Operations Research and Management Science, vol. 2, 1990. Stochastic Models. North-Holand, Chapt. 8, pp. 331?434.","DOI":"10.1016\/S0927-0507(05)80172-0"},{"key":"CR30","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"vol. 22","author":"H. Robbins","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"CR31","doi-asserted-by":"crossref","unstructured":"J. Rust, ??Numerical dynamic programming in economics??, in H. M. Amman, D. A. Kendrick, and J. Rust (eds.), Handbook of Computational Economics, vol. 1, 1996. Amsterdam, Elsevier, Amsterdam; The Netherlands: Chapt. 14.","DOI":"10.1016\/S1574-0021(96)01016-7"},{"key":"CR32","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/B978-1-55860-092-8.50012-5","volume":"vol. 2","author":"A. Sathi","year":"1989","journal-title":"Distributed Artificial Intelligence"},{"key":"CR33","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1080\/095281398146798","volume":"vol. 10","author":"S. Sen","year":"1998","journal-title":"J. Exp. Theor. Artif. Intell."},{"key":"CR34","unstructured":"P. Stone, ??Layered learning in multi-agent systems??, Ph.D. thesis, School of Computer Science, Carnegie Mellon University, 1998."},{"key":"CR35","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/0020-0255(85)90026-X","volume":"vol. 36","author":"M. Sugeno","year":"1985","journal-title":"Inform. Sci."},{"key":"CR36","volume-title":"Reinforcement Learning: An Introduction","author":"R. S. Sutton","year":"1998"},{"key":"CR37","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1162\/089976699300016070","volume":"vol. 11","author":"C. Szepesv\u00e1ri","year":"1996","journal-title":"Neural Comput."},{"key":"CR38","first-page":"487","volume-title":"Readings in Agents","author":"M. Tan","year":"1997"},{"key":"CR39","doi-asserted-by":"crossref","unstructured":"D. Vengerov and H. R. Berenji, ??Adaptive coordination among fuzzy reinforcement learning agents performing distributed dynamic load balancing??, in Proceedings of the 11th IEEE International Conference on Fuzzy Systems, 2002.","DOI":"10.1109\/FUZZ.2002.1004983"},{"key":"CR40","first-page":"279","volume":"8","author":"C. J. C. H. Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"CR41","unstructured":"G. Weiss, ??Learning to coordinate actions in multi-agent systems??, in Proceedings of the 13th International Joint Conference on Artificial Intelligence, 1993. pp. 311?316."},{"key":"CR42","volume-title":"Markov Decision Processes","author":"D. J. White","year":"1993"},{"key":"CR43","unstructured":"L. A. Zadeh, in L. A. Zadeh, R. R. Yage and R. R. Yager and R. M. Ton (eds.), Fuzzy Sets and Applications: Selected Papers, John Wiley & Sons, New York, 1987."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-004-4344-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-004-4344-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-004-4344-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,6]],"date-time":"2020-04-06T02:03:00Z","timestamp":1586138580000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-004-4344-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,5]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2005,5]]}},"alternative-id":["4344"],"URL":"https:\/\/doi.org\/10.1007\/s10458-004-4344-3","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,5]]}}}