{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:25:41Z","timestamp":1743078341602,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":39,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540400684"},{"type":"electronic","value":"9783540448266"}],"license":[{"start":{"date-parts":[[2003,1,1]],"date-time":"2003-01-01T00:00:00Z","timestamp":1041379200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/3-540-44826-8_3","type":"book-chapter","created":{"date-parts":[[2007,7,3]],"date-time":"2007-07-03T15:50:25Z","timestamp":1183477825000},"page":"33-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Cooperative Learning Using Advice Exchange"],"prefix":"10.1007","author":[{"given":"Lu\u00eds","family":"Nunes","sequence":"first","affiliation":[]},{"given":"Eug\u00e9nio","family":"Oliveira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2003,5,13]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"M. Tan. Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents. Proc. of the Tenth International Conference on Machine Learning, Amherst, MA, 330\u2013337, 1993","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"3_CR2","unstructured":"R. S. Sutton and A. G. Barto. A Temporal-Difference Model of Classical Conditioning. Tech Report GTE Labs. TR87-509.2, 1987"},{"key":"3_CR3","unstructured":"S. D. Whitehead. A complexity Analisys of Cooperative Mechanisms in Reinforcement Learning. Proc. of the 9th National Conference on Artificial Inteligence (AAAI-91), 607\u2013613, 1991"},{"key":"3_CR4","first-page":"293","volume":"8","author":"L.-J. Lin","year":"1992","unstructured":"L.-J. Lin. Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine Learning 8:293\u2013321, Kluwer Academic publishers, 1992","journal-title":"Machine Learning"},{"issue":"3","key":"3_CR5","first-page":"279","volume":"8","author":"C. J. C. H. Watkins","year":"1992","unstructured":"C. J. C. H. Watkins, P. D. Dayan. Technical note: Q-learning. Machine Learning 8,3:279\u2013292, Kluwer Academic publishers, 1992","journal-title":"Machine Learning"},{"key":"3_CR6","unstructured":"S. D. Whitehead, D. H. Ballard. A study of cooperative mechanisms for faster reinforcement learning. TR 365, Computer Science Department, University of Rochester, 1991"},{"key":"3_CR7","unstructured":"M. J. Matari\u0107. Using Communication to Reduce Locality in Distributed Multi-agent learning. Technical Report CS-96-190, Brandeis University, Dept. of Computer Science, 1996"},{"key":"3_CR8","unstructured":"C. Baroglio. Teaching by shaping. Proc. of ICML-95. Workshop on Learning by Induction vs. Learning by Demonstration, Tahoe City, CA, USA, 1995"},{"key":"3_CR9","volume-title":"Adaptation and Learning in Multiagent Systems","author":"J. A. Clouse","year":"1996","unstructured":"J. A. Clouse. Learning from an automated training agent. Gerhard Wei\u00df and Sandip Sen, editors, Adaptation and Learning in Multiagent Systems, Springer Verlag, Berlin, 1996"},{"key":"3_CR10","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1613\/jair.318","volume":"4","author":"R. I. Brafman","year":"1996","unstructured":"R. I. Brafman, M. Tennenholtz. On partially controlled multi-agent systems. Journal of Artificial Intelligence Research, 4:477\u2013507, 1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"3_CR11","unstructured":"B. Price, C. Boutilier. Implicit imitation in Multiagent Reinforcement Learning. Proc. of the Sixteenth International Conference on Machine Learning, pp. 325\u2013334. Bled, SI, 1999"},{"key":"3_CR12","unstructured":"H. R. Berenji, D. Vengerov. Advantages of Cooperation Between Reinforcement Learning Agents in Difficult Stochastic Problems. Proc. Of the Ninth IEEE International Conference on Fuzzy Systems (FUZZ-IEEE\u2019 00), 2000"},{"key":"3_CR13","unstructured":"C. Claus, C. Boutilier. The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems. Proc. of the Fifteenth National Conference on Artificial Intelligence (AAAI-98), 746\u2013752, July 1998"},{"key":"3_CR14","unstructured":"S. Kapetanakis, D. Kudenko. Reinforcement learning of coordination in cooperative multiagent systems. Proc. of the Eighteenth National Conference on Artificial Intelligence, (AAAI02), 326\u2013331, American Association for Artificial Intelligence 2002"},{"key":"3_CR15","first-page":"251","volume":"22","author":"R. Maclin","year":"1997","unstructured":"R. Maclin, J. Shavlik. Creating advicetaking reinforcement learners. Machine Learning 22:251\u2013281, 1997","journal-title":"Machine Learning"},{"key":"3_CR16","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/S1389-0417(01)00017-1","volume":"2","author":"M. J. Matari\u0107","year":"2001","unstructured":"M. J. Matari\u0107. Learning in behaviour-based multi-robot systems: policies, models and other agents. Journal of Cognitive Systems Research 2:81\u201393, Elsvier, 2001","journal-title":"Journal of Cognitive Systems Research"},{"key":"3_CR17","volume-title":"Proc. of the First International Conference on Humanoid Robotics (IEEE-RAS)","author":"O. C. Jenkins","year":"2000","unstructured":"O. C. Jenkins, M. J. Matari\u0107, S. Weber. Primitive-based movement classification for humanoid imitation. Proc. of the First International Conference on Humanoid Robotics (IEEE-RAS), Cambridge, MA, MIT, 2000"},{"key":"3_CR18","unstructured":"M. Nicoluescu, M. J. Matari\u0107. Learning and interacting in human-robot domains. K. Dautenhahn (Ed.), IEEE Transactions on systems, Man Cybernetics, special issue on Socially Intelligent Agents \u2014 The Human In The Loop, 2001"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"M. J. Matari\u0107. Sensory-motor primitives as a basis for imitation: linking perception to action and biology to robotics. C. Nehaniv & K. Dautenhahn (Eds.), Imitation in animals and artifacts, MIT Press, 2001","DOI":"10.7551\/mitpress\/3676.003.0016"},{"key":"3_CR20","unstructured":"F. J. Provost, D. N. Hennessy. Scaling Up: Distributed Machine Learning with Cooperation. Proc. of the Thirteenth National Conference on Artificial Intelligence, 1996"},{"key":"3_CR21","unstructured":"J. H. Holland. Adaptation in Natural and Artificial Systems. University of Michigan Press, 1975"},{"key":"3_CR22","volume-title":"Genetic programming: On the Programming of Computers by Means of Natural Selection","author":"J. R. Koza","year":"1992","unstructured":"J. R. Koza. Genetic programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge MA, 1992"},{"key":"3_CR23","doi-asserted-by":"crossref","first-page":"318","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel Distributed Processing: Exploration in the Microstructure of Cognition, vol. 1: Foundations","author":"D. E. Rumelhart","year":"1986","unstructured":"D. E. Rumelhart, G. E. Hinton, R. J. Wlliams. Learning internal representations by error propagation. Parallel Distributed Processing: Exploration in the Microstructure of Cognition, vol. 1: Foundations, 318\u2013362, Cambridge MA: MIT Press, 1986"},{"key":"3_CR24","volume-title":"A Genetic Algorithm for the Topological Optimization of Neural Networks","author":"R. Salustowicz","year":"1995","unstructured":"R. Salustowicz. A Genetic Algorithm for the Topological Optimization of Neural Networks. PhD Thesis, Tech. Univ. Berlin, 1995"},{"issue":"9","key":"3_CR25","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1109\/5.784219","volume":"87","author":"X. Yao","year":"1999","unstructured":"X. Yao. Evolving artificial neural networks. Proceedings of the IEEE, 87(9), 1423\u20131447, 1999","journal-title":"Proceedings of the IEEE"},{"key":"3_CR26","unstructured":"A.P. Topchy, O.A. Lebedko, V.V. Miagkikh. Fast learning in multilayered neural networks by means of hybrid evolutionary and gradient algorithms. Proc. of the International Conference on Evolutionary Computation and Its Applications, Moscow, 1996"},{"key":"3_CR27","unstructured":"K. W. C. Ku, M. W. Mak. Exploring the effects of Lamarckian and Baldwinian learning in evolving recurrent neural networks. Proc. of the IEEE International Conference on Evolutionary Computation, 617\u2013621, 1997."},{"key":"3_CR28","unstructured":"W. Erhard, T. Fink, M. M. Gutzmann, C. Rahn, A. Doering, M. Galicki, The Improvement and Comparison of different Algorithms for Optimizing Neural Networks on the MasPar {MP}-2. Neural Computation {NC}\u201998, ICSC Academic Press, Ed. M. Heiss, 617\u2013623, 1998"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"P.A. Castillo, J. Gonz\u00e1lez, J.J. Merelo, V. Rivas, G. Romero, A. Prieto. SA-Prop: Optimization of Multilayer Perceptron Parameters using Simulated Annealing. Proc. of IWANN99, 1999","DOI":"10.1007\/BFb0098224"},{"key":"3_CR30","unstructured":"T. Hogg, C. P. Williams. Solving the Really Hard problems with Cooperative Search. Proc. of the Eleventh National Conference on Artificial Intelligence (AAAI-93), 231\u2013236, 1993"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"C. Goldman, J. Rosenschein. Mutually supervised learning in multi-agent systems. Proc. of the IJCAI-95 Workshop on Adaptation and Learning in Multi-Agent Systems, Montreal, CA., August 1995","DOI":"10.1007\/3-540-60923-7_20"},{"key":"3_CR32","unstructured":"T. Thorpe. Vehicle Traffic Light Control Using SARSA. Masters Thesis, Department of Computer Science, Colorado State University, 1997"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"E. Brockfeld, R. Barlovic, A. Schadschneider, M. Schreckenberg. Optimizing Traffic Lights in a Cellular Automaton Model for City Traffic. Physical Review E 64, 2001","DOI":"10.1103\/PhysRevE.64.056132"},{"key":"3_CR34","volume-title":"Symposium on Adaptive Agents and Multi-Agent Systems (AISB\/AAMAS-II)","author":"L. Nunes","year":"2002","unstructured":"L. Nunes, E. Oliveira. On Learning By Exchanging advice. Symposium on Adaptive Agents and Multi-Agent Systems (AISB\/AAMAS-II), Imperial College, London, April 2002"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi. Optimization by simulated Annealing. Science, Vol. 220: 671\u2013680, May 1983","DOI":"10.1126\/science.220.4598.671"},{"key":"3_CR36","unstructured":"M. Glickman, K. Sycara. Evolution of Goal-Directed Behavior Using Limited Information in a Complex Environment. Proc. of the Genetic and Evolutionary Computation Conference (GECCO-99), July 1999"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"R. S. Sutton. Integrated architectures for learning planning and reacting based on approximating dynamic programming. Proc. of the Seventh International Conference on Machine Learning, 216\u201322, Morgan-Kaufman.","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"issue":"12","key":"3_CR38","doi-asserted-by":"publisher","first-page":"2221","DOI":"10.1051\/jp1:1992277","volume":"2","author":"K. Nagel","year":"1992","unstructured":"K. Nagel, M Shreckenberg. A Cellular Automaton Model for Freeway Traffic. J. Phisique I, 2(12): 2221\u20132229, 1992","journal-title":"J. Phisique I"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"S. Sen, A. Biswas, S. Debnath. Believing others: Pros and Cons. Proc. of the Fourth International Conference on Multiagent Systems, 279\u2013286, 2000","DOI":"10.1109\/ICMAS.2000.858464"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44826-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T04:02:29Z","timestamp":1737172949000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/3-540-44826-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540400684","9783540448266"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/3-540-44826-8_3","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2003]]},"assertion":[{"value":"13 May 2003","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}