{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:48:38Z","timestamp":1759772918138},"reference-count":70,"publisher":"Elsevier BV","issue":"4-5","license":[{"start":{"date-parts":[[1999,6,1]],"date-time":"1999-06-01T00:00:00Z","timestamp":928195200000},"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":["Neural Networks"],"published-print":{"date-parts":[[1999,6]]},"DOI":"10.1016\/s0893-6080(99)00024-6","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T22:54:47Z","timestamp":1027637687000},"page":"727-753","source":"Crossref","is-referenced-by-count":44,"title":["Multi-agent reinforcement learning: weighting and partitioning"],"prefix":"10.1016","volume":"12","author":[{"given":"R.","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Peterson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0893-6080(99)00024-6_BIB1","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1115\/1.3426922","article-title":"A new approach to manipulator control: the cerebellar model articulation control","volume":"97","author":"Albus","year":"1975","journal-title":"Journal of Dynamic Systems Measure and Control"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB2","unstructured":"Atkeson, C., Moore, A., and Schaal, S. (1997). Locally weighted regression. Artificial Intelligence Review."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB3","series-title":"Dynamic programming","author":"Bellman","year":"1957"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB4","series-title":"Neuro-dynamic programming","author":"Bertsekas","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB5","article-title":"Learning radial basis function networks on-line","author":"Blanzieri","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB6","first-page":"369","article-title":"Generalization in reinforcement learning: safely approximating the value function","volume":"7","author":"Boyan","year":"1995"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB7","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Machine Learning"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB8","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/BF00117832","article-title":"Stacked regressions","volume":"24","author":"Breiman","year":"1996","journal-title":"Machine Learning"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB9","unstructured":"Breiman, L. (1996c). Bias, variance and arcing classifiers. Technical Report 460. Berkeley: University of California."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB10","series-title":"Classification and regression","author":"Breiman","year":"1984"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB11","article-title":"Reinforcement learning with perceptual aliasing: the perceptual distinction approach","author":"Chrisman","year":"1993"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB12","article-title":"Feudal reinforcement learning","author":"Dayan","year":"1993"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB13","unstructured":"Dietterich, T. (1997). Hierarchical reinforcement learning with MAXQ value function decomposition. Technical report. ftp:\/\/www.cs.orst.edu\/"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB14","unstructured":"Dorigo, M., and Gambardella, L. (1995). Ant-Q: a reinforcement learning approach to combinatorial optimization. Technical Report 95-01. Belgium: Universite Libre de Bruxelles."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB15","article-title":"Improving regressors using boosting techniques","author":"Drucker","year":"1997"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB16","unstructured":"Erickson, M., and Kruschke, J. (1996). Rules and examplars in category learning (Manuscript)."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB17","article-title":"Experiments with a new boosting algorithm","author":"Freund","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB18","unstructured":"Hashem, S. (1993). Optimal linear combinations of neural networks. PhD Thesis, Purdue, Indiana: Purdue University."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB19","series-title":"Introduction to the theory of neural computation","author":"Hertz","year":"1991"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB20","unstructured":"Humphrys, M. (1996). W-learning: a simple RL-based society of mind. Technical report 362, Cambridge, UK: University of Cambridge, Computer Laboratory."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB21","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1162\/neco.1997.9.2.369","article-title":"Bias\/variance analysis of mixtures-of-experts architectures","volume":"9","author":"Jacobs","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB22","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Computation."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB23","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","article-title":"Hierarchical mixtures of experts and the EM algorithm","volume":"6","author":"Jordan","year":"1994","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB24","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":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB25","article-title":"Neural network ensembles, cross validation, and active learning","author":"Krogh","year":"1995"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB26","doi-asserted-by":"crossref","unstructured":"Kubat, M. (1997). Decision trees can initialize radial-basis-function networks (Manuscript).","DOI":"10.1109\/72.712154"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB27","unstructured":"Lane, S., Handelman, D., & Gelfand, J. (1992). Theory and development of higher-order CMAC neural networks. IEEE Control Systems, pp. 23\u201331."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB28","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/BF00992699","article-title":"Self-improving reactive agents based on reinforcement learning, planning, and teaching","volume":"8","author":"Lin","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB29","article-title":"Pruning adaptive boosting","author":"Margineantu","year":"1997"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB30","article-title":"Reward functions for accelerated learning","author":"Mataric","year":"1995"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB31","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3118.003.0039","article-title":"Learning to use selective attention and short-term memory in sequential tasks","author":"McCallum","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB32","article-title":"Bias, variance and the combination of least squares estimators","author":"Meir","year":"1995"},{"issue":"3\/4","key":"10.1016\/S0893-6080(99)00024-6_BIB33","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1080\/095400996116848","article-title":"Reducing variance of committee prediction with resampling techniques","volume":"8","author":"Parmanto","year":"1996","journal-title":"Connection Science"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB34","unstructured":"Perrone, M. (1993). Improving regression estimation: averaging methods for variance reduction with extensions to general convex measure optimization. PhD Thesis, Brown University. Providence, RI."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB35","article-title":"An RBF network alternative to a hybrid architecture. Anchorage, Alaska","author":"Peterson","year":"1998"},{"issue":"9","key":"10.1016\/S0893-6080(99)00024-6_BIB36","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1109\/5.58326","article-title":"Networks for approximation and learning","volume":"78","author":"Poggio","year":"1990","journal-title":"Proceedings of IEEE"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB37","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/BF00116251","article-title":"Inductive learning of decision trees","volume":"1","author":"Quinlan","year":"1986","journal-title":"Machine Learning"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB38","article-title":"Bagging, Boosting and C4.5","author":"Quinlan","year":"1996"},{"issue":"3\/4","key":"10.1016\/S0893-6080(99)00024-6_BIB39","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1080\/095400996116811","article-title":"Bootstrapping with noise: an effective regularization technique","volume":"8","author":"Raviv","year":"1996","journal-title":"Connection Science"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB40","article-title":"Learning goal-decomposition rules using exercises","author":"Reddy","year":"1997"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB41","unstructured":"Rosca, J. (1997). Hierarchical learning with procedural abstraction mechanisms. PhD Thesis, Rochester, NY: Department of Computer Science, University of Rochester."},{"issue":"3\/4","key":"10.1016\/S0893-6080(99)00024-6_BIB42","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1080\/095400996116820","article-title":"Ensemble learning using decorrelated neural networks","volume":"8","author":"Rosen","year":"1996","journal-title":"Connection Science"},{"issue":"2","key":"10.1016\/S0893-6080(99)00024-6_BIB43","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1109\/72.80339","article-title":"Tree-structured adaptive networks for function approximation in high-dimensional spaces","volume":"2","author":"Sanger","year":"1991","journal-title":"IEEE Transaction on Neural Networks"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB44","article-title":"From isolation to cooperation: an alternative view of a system of experts","author":"Schaal","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB45","article-title":"Boosting the margin: a new explanation for the effectiveness of voting methods","author":"Shcapire","year":"1997"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB46","doi-asserted-by":"crossref","unstructured":"Singh, S. (1994). Learning to solve Markovian decision processes. PhD Thesis, Amherst, MA: University of Massachusetts","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB47","series-title":"Advances in Neural Information Processing Systems","article-title":"Reinforcement learning with soft state aggregation","author":"Singh","year":"1994"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB48","unstructured":"Sun, R. (1997). Planning from reinforcement learning. Technical report TR-CS-97-0027, Tuscaloosa, AL: University of Alabama."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB49","series-title":"Computational architectures integrating neural and symbolic procedures","year":"1994"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB50","series-title":"Connectionist-symbolic integration","article-title":"A hybrid agent architecture for reactive sequential decision making","author":"Sun","year":"1997"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB51","doi-asserted-by":"crossref","DOI":"10.1109\/CIRA.1997.613863","article-title":"A hybrid model for learning sequential navigation","author":"Sun","year":"1997"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB52","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/S0020-0255(98)00007-3","article-title":"Some experiments with a hybrid model for learning sequential decision making","volume":"111","author":"Sun","year":"1998","journal-title":"Information Sciences"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB53","article-title":"Bottom-up skill learning in reactive sequential decision tasks","author":"Sun","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB55","article-title":"Integrated architectures for learning, planning","author":"Sutton","year":"1990"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB56","article-title":"Generalization in reinforcement learning: successful examples using sparse coarse coding","volume":"8","author":"Sutton","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB57","article-title":"Hierarchical explanation-based reinforcement learning","author":"Tadepalli","year":"1997"},{"issue":"1","key":"10.1016\/S0893-6080(99)00024-6_BIB58","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/TSMC.1985.6313399","article-title":"Fuzzy identification of systems and its applications to modeling and control","volume":"15","author":"Takagi","year":"1985","journal-title":"IEEE Transactions on Systems Man and Cybernetics"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB59","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1162\/neco.1997.9.5.1163","article-title":"Averaging regularized estimators","volume":"9","author":"Taniguchi","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB60","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0921-8890(95)00005-Z","article-title":"Reinforcement learning of multiple tasks using a hierarchical CMAC architecture","volume":"15","author":"Tham","year":"1995","journal-title":"Robotics and Autonomous Systems"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB61","article-title":"Finding structure in reinforcement learning","volume":"7","author":"Thrun","year":"1995"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB62","article-title":"Stacking bagged and dagged models","author":"Ting","year":"1997"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB63","article-title":"Combining estimators using non-constant weighting functions","volume":"7","author":"Tresp","year":"1995"},{"issue":"3\/4","key":"10.1016\/S0893-6080(99)00024-6_BIB64","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1080\/095400996116839","article-title":"Error correlation and error reduction in ensemble classifiers","volume":"8","author":"Tumer","year":"1996","journal-title":"Connection Science"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB65","doi-asserted-by":"crossref","DOI":"10.1109\/ICNN.1996.548872","article-title":"Generalization error of ensemble estimators","author":"Ueda","year":"1996"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB66","article-title":"Approximation with neural networks","author":"van der Smagt","year":"1995"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB67","unstructured":"Watkins, C. (1989). Learning with delayed rewards. PhD Thesis, Cambridge, UK: Cambridge University."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB68","unstructured":"Wiering, M., and Schmidhuber, J. (1996). HQ-learning. TR IDSIA-95-96."},{"key":"10.1016\/S0893-6080(99)00024-6_BIB69","article-title":"A complexity analysis of cooperative mechanisms in reinforcement learning","author":"Whitehead","year":"1993"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB70","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Networks"},{"key":"10.1016\/S0893-6080(99)00024-6_BIB71","article-title":"An alternative model for mixtures of experts","volume":"7","author":"Xu","year":"1995"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608099000246?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608099000246?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T17:11:21Z","timestamp":1704129081000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608099000246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,6]]},"references-count":70,"journal-issue":{"issue":"4-5","published-print":{"date-parts":[[1999,6]]}},"alternative-id":["S0893608099000246"],"URL":"https:\/\/doi.org\/10.1016\/s0893-6080(99)00024-6","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[1999,6]]}}}