{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T08:26:55Z","timestamp":1725870415599},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319490489"},{"type":"electronic","value":"9783319490496"}],"license":[{"start":{"date-parts":[[2016,11,9]],"date-time":"2016-11-09T00:00:00Z","timestamp":1478649600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-49049-6_33","type":"book-chapter","created":{"date-parts":[[2016,11,8]],"date-time":"2016-11-08T01:24:58Z","timestamp":1478568298000},"page":"453-467","source":"Crossref","is-referenced-by-count":5,"title":["Communication-Less Cooperative Q-Learning Agents in Maze Problem"],"prefix":"10.1007","author":[{"given":"Fumito","family":"Uwano","sequence":"first","affiliation":[]},{"given":"Keiki","family":"Takadama","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,11,9]]},"reference":[{"key":"33_CR1","unstructured":"Yong-Jae\u00a0Kim Kui-Hong\u00a0Park and Jong-Hwan Kim. Modular q-learning based multi-agent cooperation for robot soccer. Robotics and Autonomous System, pages 3026\u20133033, 2015."},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Michael Camara, Oliver Bonham-Carter, and Janyl Jumadinova. A multi-agent system with reinforcement learning agents for biomedical text mining. In Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics, BCB \u201915, pages 634\u2013643, New York, NY, USA, 2015. ACM.","DOI":"10.1145\/2808719.2812596"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"H.\u00a0Iima and Y.\u00a0Kuroe. Swarm reinforcement learning methods improving certainty of learning for a multi-robot formation problem. CEC, pages 3026\u20133033, May 2015.","DOI":"10.1109\/CEC.2015.7257266"},{"issue":"6","key":"33_CR4","doi-asserted-by":"crossref","first-page":"926","DOI":"10.20965\/jaciii.2013.p0926","volume":"17","author":"Y Ichikawa","year":"2013","unstructured":"Y.\u00a0Ichikawa and K.\u00a0Takadama. Designing internal reward of reinforcement learning agents in multi-step dilemma problem. Journal of Computational Intelligence and Intelligent Informatics, JACIII, 17(6):926\u2013931, 2013.","journal-title":"Journal of Computational Intelligence and Intelligent Informatics, JACIII"},{"key":"33_CR5","unstructured":"M.\u00a0Gini M.\u00a0Elidrisi, N.\u00a0Johnson and J.\u00a0Crandall. Fast adaptive learning in repeated stochastic games by game abstraction. AAMAS, pages 1141\u20131148, May 2014."},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Prabuchandran\u00a0K. J., Hemanth Kumar\u00a0A. N, and S.\u00a0Bhatnagar. Multi-agent reinforcement learning for traffic signal control. In Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on, pages 2529\u20132534, Oct 2014.","DOI":"10.1109\/ITSC.2014.6958095"},{"key":"33_CR7","volume-title":"A selection-mutation model for q-learning in multi-agent systems","author":"Katja Verbeeck Karl Tuyls","year":"2015","unstructured":"Katja\u00a0Verbeeck Karl\u00a0Tuyls and Tom Lenaerts. A selection-mutation model for q-learning in multi-agent systems. Robotics and Autonomous System, pages 3026\u20133033, May 2015."},{"key":"33_CR8","unstructured":"Alessandro\u00a0Lazaric Enrique Munoz\u00a0de Cote and Marcello Restelli. Learning to cooperate in multi-agent social dilemmas. AAMAS, pages 783\u2013785, May 2006."},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Ming Tan. Multi-agent reinforcement learning: Independent vs. cooperative agents. In In Proceedings of the Tenth International Conference on Machine Learning, pages 330\u2013337. Morgan Kaufmann, 1993.","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"N.\u00a0Ono and K.\u00a0Fukumoto, editors. Multi-agent reinforcement learning: A modular approach, 1996.","DOI":"10.1007\/3-540-62934-3_39"},{"key":"33_CR11","volume-title":"Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"R.S. Sutton and A.G. Barto. Reinforcement Learning. Bradford Books\/MIT Press, Cambridge, MA, 1998."}],"container-title":["Proceedings in Adaptation, Learning and Optimization","Intelligent and Evolutionary Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49049-6_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,15]],"date-time":"2019-09-15T06:46:05Z","timestamp":1568529965000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-49049-6_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,9]]},"ISBN":["9783319490489","9783319490496"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49049-6_33","relation":{},"ISSN":["2363-6084","2363-6092"],"issn-type":[{"type":"print","value":"2363-6084"},{"type":"electronic","value":"2363-6092"}],"subject":[],"published":{"date-parts":[[2016,11,9]]}}}