{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T07:04:32Z","timestamp":1748070272135},"reference-count":12,"publisher":"Elsevier BV","issue":"1-3","license":[{"start":{"date-parts":[[1999,10,1]],"date-time":"1999-10-01T00:00:00Z","timestamp":938736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[1999,10]]},"DOI":"10.1016\/s0925-2312(98)00117-9","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T18:55:54Z","timestamp":1027623354000},"page":"93-105","source":"Crossref","is-referenced-by-count":11,"title":["Exploration tuned reinforcement function"],"prefix":"10.1016","volume":"28","author":[{"given":"Juan Miguel","family":"Santos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claude","family":"Touzet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0925-2312(98)00117-9_BIB1","unstructured":"D. Ackley, M. Littman, Interactions between learning and evolution, in: C.G. Langton, C. Taylor, J.D. Farmer, S. Rasmussen (Eds.), Artificial Life II, SFI Studies in the Sciences of Complexity, vol. X, Addison-Wesley, Reading, MA, 1991, pp. 487\u2013509."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB2","doi-asserted-by":"crossref","unstructured":"P. Dayan, T. Sejnowski, TD(l) Convergence with probability 1, Mach. Learning 14(3) (1994) 341\u2013362.","DOI":"10.1007\/BF00993978"},{"key":"10.1016\/S0925-2312(98)00117-9_BIB3","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: a survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB4","unstructured":"L.-J. Lin, T.M. Mitchell, Memory approaches to reinforcement learning in non-Markovian domains, Technical Report CMU-CS-92-138, Carnegie Mellon University, School of Computer Science, 1992."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB5","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/0004-3702(92)90058-6","article-title":"Automatic programming of behavior-based robots using reinforcement learning","volume":"55","author":"Mahadevan","year":"1992","journal-title":"Artif. Intell."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB6","doi-asserted-by":"crossref","unstructured":"M.J. Mataric, Reward functions for accelerated learning, in: W.W. Cohen, H. Hirsh (Eds.), Machine Learning: Proceedings of the Eleventh International Conference, Morgan Kaufmann Publishers, Los Altos, LA, 1994, pp. 181\u2013189.","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"10.1016\/S0925-2312(98)00117-9_BIB7","unstructured":"S. Sehad, C. Touzet, Reinforcement learning and neural reinforcement learning, Proceedings of ESANN\u201994, 1994."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB8","unstructured":"S.B. Thrun, Efficient exploration in reinforcement learning, Technical Report CMU-CS-92-102 Carnegie-Mellon University, 1992."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB9","unstructured":"S. Thrun, Exploration in active learning, in: M. Arbib (Ed.), Handbook of Brain and Neural Networks, MIT Press, 1996, pp. 381\u2013384."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB10","doi-asserted-by":"crossref","unstructured":"C. Touzet, Neural reinforcement learning for behaviour synthesis, N. Sharkey (Guest Ed.), Robotics and Autonomous Systems, vol. 22, Special issue on Learning Robot: the New Wave, Elsevier, 1997, pp. 251\u2013281.","DOI":"10.1016\/S0921-8890(97)00042-0"},{"key":"10.1016\/S0925-2312(98)00117-9_BIB11","unstructured":"C. Touzet, S. Sen, Learning agents, invited paper at the First Conference on Autonomous Agents, Marina del Rey, CA, 1997."},{"key":"10.1016\/S0925-2312(98)00117-9_BIB12","unstructured":"P. Zhang, S. Canu, Indirect adaptive exploration in entropy-based reinforcement learning, Proceedings of ICANN\u201996, 1996."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231298001179?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231298001179?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,1,28]],"date-time":"2020-01-28T19:53:44Z","timestamp":1580241224000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231298001179"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,10]]},"references-count":12,"journal-issue":{"issue":"1-3","published-print":{"date-parts":[[1999,10]]}},"alternative-id":["S0925231298001179"],"URL":"https:\/\/doi.org\/10.1016\/s0925-2312(98)00117-9","relation":{},"ISSN":["0925-2312"],"issn-type":[{"type":"print","value":"0925-2312"}],"subject":[],"published":{"date-parts":[[1999,10]]}}}