{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:33Z","timestamp":1725558993128},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540252603"},{"type":"electronic","value":"9783540322740"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/978-3-540-32274-0_12","type":"book-chapter","created":{"date-parts":[[2010,7,5]],"date-time":"2010-07-05T16:21:44Z","timestamp":1278346904000},"page":"185-204","source":"Crossref","is-referenced-by-count":5,"title":["Advice-Exchange Between Evolutionary Algorithms and Reinforcement Learning Agents: Experiments in the Pursuit Domain"],"prefix":"10.1007","author":[{"given":"Lu\u00eds","family":"Nunes","sequence":"first","affiliation":[]},{"given":"Eug\u00e9nio","family":"Oliveira","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"doi-asserted-by":"crossref","unstructured":"Clouse, J.A.: On integrating apprentice learning and reinforcement learning. PhD thesis, University of Massachusetts, Department of Computer Science (1997)","key":"12_CR1","DOI":"10.1016\/S0166-4115(97)80108-2"},{"doi-asserted-by":"crossref","unstructured":"Nunes, L., Oliveira, E.: Advice-exchange in heterogeneous groups of learning agents. Technical Report 1 12\/02, FEUP\/LIACC (2002)","key":"12_CR2","DOI":"10.1145\/860575.860807"},{"unstructured":"Whitehead, S.D.: A complexity analysis of cooperative mechanisms in reinforcement learning. In: Proc. of the 9th National Conf. on AI (AAAI 1991), pp. 607\u2013613 (1991)","key":"12_CR3"},{"unstructured":"Clouse, J.A., Utgoff, P.E.: Two kinds of training information for evaluation function learning. In: Proc. of AAAI 1991 (1991)","key":"12_CR4"},{"doi-asserted-by":"crossref","unstructured":"Clouse, J., Utgoff, P.: A teaching method for reinforcement learning. In: Proc. of the 9th Int. Conf. on Machine Learning, pp. 92\u2013101 (1992)","key":"12_CR5","DOI":"10.1016\/B978-1-55860-247-2.50017-6"},{"key":"12_CR6","first-page":"293","volume":"8","author":"L.J. Lin","year":"1992","unstructured":"Lin, L.J.: Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine Learning\u00a08, 293\u2013321 (1992)","journal-title":"Machine Learning"},{"doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. Proc. of the Tenth Int. Conf. on Machine Learning, 330\u2013337 (1993)","key":"12_CR7","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"unstructured":"Price, B., Boutilier, C.: Implicit imitation in multiagent reinforcement learning. Proc. of the Sixteenth Int. Conf. on Machine Learning, 325\u2013334 (1999)","key":"12_CR8"},{"unstructured":"Sen, S., Kar, P.P.: Sharing a concept. In: Working Notes of the AAAI 2002 Spring Symposium on Collaborative Learning Agents (2002)","key":"12_CR9"},{"key":"12_CR10","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.D.: Technical note: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"12_CR11","first-page":"318","volume":"1","author":"D.E. Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Parallel Distributed Processing: Exploration in the Microstructure of Cognition\u00a01, 318\u2013362 (1986)","journal-title":"Parallel Distributed Processing: Exploration in the Microstructure of Cognition"},{"doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04 (1996)","key":"12_CR12","DOI":"10.1613\/jair.301"},{"unstructured":"Nunes, L., Oliveira, E.: Advice exchange between evolutionary algorithms and reinforcement learning agents: Experimental results in the pursuit domain. Technical Report 2 03\/03, FEUP\/LIACC (2003)","key":"12_CR13"},{"unstructured":"Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press (1975)","key":"12_CR14"},{"key":"12_CR15","volume-title":"Genetic programming: On the Programming of Computers by Means of Natural Selection","author":"J.R. Koza","year":"1992","unstructured":"Koza, J.R.: Genetic programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)"},{"unstructured":"Salustowicz, R.: A Genetic Algorithm for the Topological Optimization of Neural Networks. PhD thesis, Tech. Univ. Berlin (1995)","key":"12_CR16"},{"key":"12_CR17","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1109\/5.784219","volume":"87","author":"X. Yao","year":"1999","unstructured":"Yao, X.: Evolving artificial neural networks. Proc. of IEEE.\u00a087, 1423\u20131447 (1999)","journal-title":"Proc. of IEEE."},{"unstructured":"Glickman, M., Sycara, K.: Evolution of goal-directed behavior using limited information in a complex environment. In: Proc. of the Genetic and Evolutionary Computation Conference, GECCO 1999 (1999)","key":"12_CR18"},{"unstructured":"Nunes, L., Oliveira, E.: On learning by exchanging advice. In: Proc. of the First Symposium on Adaptive Agents and Multi-Agent Systems, AISB 2002 (2002)","key":"12_CR19"},{"unstructured":"Benda, M., Jagannathan, V., Dodhiawalla, R.: On optimal cooperation of knowledge resources. Technical Report BCS G-2012-28, Boeing AI Center, Boeing Computer Services, Bellevue, WA (1985)","key":"12_CR20"},{"unstructured":"Haynes, T., Wainwright, R., Sen, S., Schoenfeld, D.: Strongly typed genetic programming in evolving cooperation strategies. In: Proc. of the Sixth Int. Conf. on Genetic Algorithms, pp. 271\u2013278 (1995)","key":"12_CR21"},{"unstructured":"Sen, S., Sekaran, M., Hale, J.: Lerning to coordinate without sharing information. In: Proc. of the National Conf. on AI, pp. 426\u2013431 (1994)","key":"12_CR22"},{"key":"12_CR23","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1080\/095281398146798","volume":"10","author":"S. Sen","year":"1998","unstructured":"Sen, S., Sekaran, M.: Individual learning of coordination knowledge. Journal of Experimental, Theoretical Artificial Intelligence\u00a010, 333\u2013356 (1998)","journal-title":"Journal of Experimental, Theoretical Artificial Intelligence"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems II"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-32274-0_12.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T18:46:12Z","timestamp":1685645172000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-32274-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540252603","9783540322740"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-32274-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}