{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T10:28:21Z","timestamp":1762252101755,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783662436448"},{"type":"electronic","value":"9783662436455"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-662-43645-5_2","type":"book-chapter","created":{"date-parts":[[2014,6,27]],"date-time":"2014-06-27T13:25:24Z","timestamp":1403875524000},"page":"15-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Heuristically-Accelerated Reinforcement Learning: A Comparative Analysis of Performance"],"prefix":"10.1007","author":[{"given":"Murilo Fernandes","family":"Martins","sequence":"first","affiliation":[]},{"given":"Reinaldo A. C.","family":"Bianchi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,6,28]]},"reference":[{"key":"2_CR1","unstructured":"Watkins, C.: Learning from delayed rewards. Ph.D. thesis, University of Cambridge, England (1989)"},{"key":"2_CR2","series-title":"Adaptive Computation and Machine Learning","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning. MIT Press, Cambridge (1998)"},{"issue":"1","key":"2_CR3","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1023\/A:1007562800292","volume":"33","author":"M Wiering","year":"1998","unstructured":"Wiering, M., Schmidhuber, J.: Fast online q(lambda). Mach. Learn. 33(1), 105\u2013115 (1998)","journal-title":"Mach. Learn."},{"key":"2_CR4","unstructured":"Ribeiro, C., Szepesv\u00e1ri, C.: Q-learning combined with spreading: convergence and results. In: ISRF-IEE International Conference on Intelligent and Cognitive Systems (Neural Networks Symposium), pp. 32\u201336 (1996)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Ribeiro, C., Pegoraro, R., Costa, A.: Experience generalization for concurrent reinforcement learners: the minimax-qs algorithm. In: Proceedings of the First International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 1239\u20131245. ACM, NY (2002)","DOI":"10.1145\/545056.545106"},{"key":"2_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/978-3-540-28645-5_25","volume-title":"Advances in Artificial Intelligence \u2013 SBIA 2004","author":"RAC Bianchi","year":"2004","unstructured":"Bianchi, R.A.C., Ribeiro, C.H.C., Costa, A.H.R.: Heuristically accelerated Q\u2013learning: a new approach to speed up reinforcement learning. In: Bazzan, A.L.C., Labidi, S. (eds.) SBIA 2004. LNCS (LNAI), vol. 3171, pp. 245\u2013254. Springer, Heidelberg (2004)"},{"issue":"1\u20133","key":"2_CR7","first-page":"283","volume":"22","author":"J Peng","year":"1996","unstructured":"Peng, J., Williams, R.: Incremental multi-step q-learning. Mach. Learn. 22(1\u20133), 283\u2013290 (1996)","journal-title":"Mach. Learn."},{"issue":"4","key":"2_CR8","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TSMCB.2008.920231","volume":"38","author":"M Wiering","year":"2008","unstructured":"Wiering, M., van Hasselt, H.: Ensemble algorithms in reinforcement learning. IEEE Trans. Syst. Man Cybern. Part B 38(4), 930\u2013936 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"issue":"2","key":"2_CR9","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10732-007-9031-5","volume":"14","author":"R Bianchi","year":"2008","unstructured":"Bianchi, R., Ribeiro, C., Costa, A.: Accelerating autonomous learning by using heuristic selection of actions. J. Heuristics 14(2), 135\u2013168 (2008)","journal-title":"J. Heuristics"},{"key":"2_CR10","unstructured":"Bianchi, R., Ribeiro, C., Costa, A.: Heuristic selection of actions in multiagent reinforcement learning. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, pp. 690\u2013696. Morgan Kaufmann Publishers Inc. (2007)"},{"key":"2_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/978-3-642-24769-9_27","volume-title":"Progress in Artificial Intelligence","author":"JA Gurzoni Jr","year":"2011","unstructured":"Gurzoni Jr, J.A., Tonidandel, F., Bianchi, R.A.C.: Market-based dynamic task allocation using heuristically accelerated reinforcement learning. In: Antunes, L., Pinto, H.S. (eds.) EPIA 2011. LNCS, vol. 7026, pp. 365\u2013376. Springer, Heidelberg (2011)"},{"key":"2_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/978-3-642-02998-1_7","volume-title":"Case-Based Reasoning Research and Development","author":"RAC Bianchi","year":"2009","unstructured":"Bianchi, R.A.C., Ros, R., Lopez de Mantaras, R.: Improving reinforcement learning by using case based heuristics. In: McGinty, L., Wilson, D.C. (eds.) ICCBR 2009. LNCS, vol. 5650, pp. 75\u201389. Springer, Heidelberg (2009)"},{"issue":"2","key":"2_CR13","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1109\/TCYB.2013.2253094","volume":"44","author":"R Bianchi","year":"2013","unstructured":"Bianchi, R., Martins, M., Ribeiro, C., Costa, A.: Heuristically-accelerated multiagent reinforcement learning. IEEE Trans. Cybern. 44(2), 252\u2013265 (2013)","journal-title":"IEEE Trans. Cybern."},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the 11th International Conference on Machine Learning (ML-94), pp. 157\u2013163. Morgan Kaufmann, New Brunswick (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"}],"container-title":["Lecture Notes in Computer Science","Towards Autonomous Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-43645-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T18:17:12Z","timestamp":1676398632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-662-43645-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783662436448","9783662436455"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-43645-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"28 June 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}