{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:47:02Z","timestamp":1725518822267},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540881919"},{"type":"electronic","value":"9783540881926"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-88192-6_61","type":"book-chapter","created":{"date-parts":[[2008,9,29]],"date-time":"2008-09-29T08:05:59Z","timestamp":1222675559000},"page":"596-603","source":"Crossref","is-referenced-by-count":0,"title":["A Design of Reward Function Based on Knowledge in Multi-agent Learning"],"prefix":"10.1007","author":[{"given":"Bo","family":"Fan","sequence":"first","affiliation":[]},{"given":"Jiexin","family":"Pu","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"61_CR1","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/S1389-0417(01)00015-8","volume":"2","author":"M.L. Littman","year":"2001","unstructured":"Littman, M.L.: Value-function reinforcement learning in Markov games. Journal of Cognitive Systems Research\u00a02, 55\u201366 (2001)","journal-title":"Journal of Cognitive Systems Research"},{"key":"61_CR2","first-page":"195","volume-title":"Proceedings of the Sixth Conference on Theoretical Aspects of Rationality and Knowledge","author":"C. Boutilier","year":"1996","unstructured":"Boutilier, C.: Planning, Learning and Coordination in Multi-agent Decision Processes. In: Shoham, Y. (ed.) Proceedings of the Sixth Conference on Theoretical Aspects of Rationality and Knowledge, pp. 195\u2013210. Morgan Kaufmann, San Francisco (1996)"},{"issue":"2","key":"61_CR3","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1613\/jair.1332","volume":"22","author":"M. Bowling","year":"2004","unstructured":"Bowling, M., Veloso, M.: Existence of Multiagent Equilibria with Limited Agents. J of Artificial Intelligence Research\u00a022(2), 353\u2013384 (2004)","journal-title":"J of Artificial Intelligence Research"},{"issue":"3","key":"61_CR4","first-page":"279","volume":"8","author":"C.J.C.H. Watkons","year":"1992","unstructured":"Watkons, C.J.C.H., Dayan, P.: Q-leanign. Machine Learning\u00a08(3), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"61_CR5","doi-asserted-by":"crossref","unstructured":"Matalic, M.J.: Reward Functions for Accelerated Learning. In: Proc. Int. Conf. on Machine learning, pp. 181\u2013189 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"61_CR6","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/S1389-0417(01)00017-1","volume":"2","author":"M.J. Mataric","year":"2001","unstructured":"Mataric, M.J.: Learning in behavior-based multi-robot systems: policies, models, and other agents. Journal of Cognitive Systems Research\u00a02, 81\u201393 (2001)","journal-title":"Journal of Cognitive Systems Research"},{"key":"61_CR7","doi-asserted-by":"crossref","unstructured":"Inoue, K., Ota, J., Katayama, T., Arai, T.: Acceleration of Reinforcement Learning by A Mobile Robot Using Generalized Rules. In: Proc. IEEE Int. Conf. Intelligent Robots and Systems, pp. 885\u2013890 (2000)","DOI":"10.1109\/IROS.2000.893131"},{"key":"61_CR8","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1023\/A:1007968115863","volume":"21","author":"H.C. Calos","year":"1998","unstructured":"Calos, H.C.: Embedding a Priori Knowledge in Reinforcement Learning. Journal of Intelligent and Robotics Systems\u00a021, 51\u201371 (1998)","journal-title":"Journal of Intelligent and Robotics Systems"},{"key":"61_CR9","first-page":"251","volume":"22","author":"R. Maclin","year":"1996","unstructured":"Maclin, R., Shavlik, J.W.: Creating Advice-Taking Reinforcement Learners. Machine Learning\u00a022, 251\u2013281 (1996)","journal-title":"Machine Learning"},{"key":"61_CR10","unstructured":"Smart, W.D., Kaelbling, L.P.: Effective reinforcement learning for mobile robots. In: Proceedings of the IEEE International Conference on Robotics and Automation (2002), www.ai.mit.edu\/people\/lpk\/papers\/icra2002.pdf"},{"key":"61_CR11","unstructured":"http:\/\/www.fira.net"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-88192-6_61.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T11:58:07Z","timestamp":1619524687000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-88192-6_61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540881919","9783540881926"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-88192-6_61","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}