{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:14:52Z","timestamp":1771024492088,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2008,4,23]],"date-time":"2008-04-23T00:00:00Z","timestamp":1208908800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2008,10]]},"DOI":"10.1007\/s10458-008-9046-9","type":"journal-article","created":{"date-parts":[[2008,4,22]],"date-time":"2008-04-22T19:08:02Z","timestamp":1208891282000},"page":"320-338","source":"Crossref","is-referenced-by-count":69,"title":["Analyzing and visualizing multiagent rewards in dynamic and stochastic domains"],"prefix":"10.1007","volume":"17","author":[{"given":"Adrian K.","family":"Agogino","sequence":"first","affiliation":[]},{"given":"Kagan","family":"Tumer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2008,4,23]]},"reference":[{"key":"9046_CR1","unstructured":"Agogino, A., Martin, C., & Ghosh, J. (1998). Principal curve classifier\u2014A nonlinear approach to pattern classification. In Proceedings of International Joint Conference on Neural Networks, Anchorage, Alaska."},{"key":"9046_CR2","doi-asserted-by":"crossref","unstructured":"Agogino, A., Martin, C., & Ghosh, J. (1999). Visualization of radial basis function networks. In Proceedings of International Joint Conference on Neural Networks. Washington, DC.","DOI":"10.1109\/IJCNN.1999.831130"},{"key":"9046_CR3","doi-asserted-by":"crossref","unstructured":"Agogino, A., & Tumer, K. (2004). Efficient evaluation functions for multi-rover systems. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2004) (pp. 1\u201312). Seattle, WA.","DOI":"10.1007\/978-3-540-24854-5_1"},{"key":"9046_CR4","doi-asserted-by":"crossref","unstructured":"Agogino, A., & Tumer, K. (2005). Multi agent reward analysis for learning in noisy domains. In Proceedings of the Fourth International Joint Conference on Autonomous Agents and Multi-Agent Systems, Utrecht, Netherlands.","DOI":"10.1145\/1082473.1082486"},{"key":"9046_CR5","unstructured":"Baird, L., & Moore, A. (1999). Gradient descent for general reinforcement learning. In Advances in Neural Information Processing Systems (NIPS) (pp. 968\u2013974). Cambridge, MA."},{"key":"9046_CR6","doi-asserted-by":"crossref","unstructured":"Bishof, H., Pinz, A., & Kropatsch, W. G. (1992). Visualization methods for neural networks. In 11th International Conference on Pattern Recognition (pp. 581\u2013585). The Hague, Netherlands.","DOI":"10.1109\/ICPR.1992.201845"},{"key":"9046_CR7","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural networks for pattern recognition","author":"C.M. Bishop","year":"1995","unstructured":"Bishop C.M. (1995). Neural networks for pattern recognition. Oxford University Press, New York"},{"key":"9046_CR8","doi-asserted-by":"crossref","unstructured":"Chalkiadakis, G., & Boutilier, C. (2003). Coordination in multiagent reinforcement learning: A Bayesian approach. In Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-03), Melbourne, Australia.","DOI":"10.1145\/860575.860689"},{"key":"9046_CR9","first-page":"1017","volume-title":"Advances in neural information processing systems-8","author":"R.H. Crites","year":"1996","unstructured":"Crites R.H. and Barto A.G. (1996). Improving elevator performance using reinforcement learning. In: Touretzky, D.S., Mozer, M.C. and Hasselmo, M.E. (eds) Advances in neural information processing systems-8, pp 1017\u20131023. MIT Press, Cambridge, MA"},{"issue":"1\u20132","key":"9046_CR10","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1023\/B:AGNT.0000019689.48746.3e","volume":"9","author":"C.B. Excelente-Toledo","year":"2004","unstructured":"Excelente-Toledo C.B. and Jennings N.R. (2004). The dynamic selection of coordination mechanisms. Journal of Autonomous Agents and Multi-Agent Systems 9(1\u20132): 55\u201385","journal-title":"Journal of Autonomous Agents and Multi-Agent Systems"},{"key":"9046_CR11","unstructured":"Gallagher, M., & Downs, T. (1997). Visualization of learning in neural networks using principal component analysis. In International Conference on Computational Intelligence and Multimedia Applications (pp. 327\u2013331)."},{"key":"9046_CR12","unstructured":"Guestrin, C., Hauskrecht, M., & Kveton, B. (2004). Solving factored MDPs with continuous and discrete variables. In Proceedings of the 20th Conference on Uncertainty in Artificial Intelligence (pp. 235\u2013242)."},{"key":"9046_CR13","unstructured":"Guestrin, C., Koller, D., & Parr, R. (2001a). Max-norm projections for factored MDPs. In Proceedings of the International Joint Conference on Artificial Intelligence."},{"key":"9046_CR14","unstructured":"Guestrin, C., Koller, D., & Parr, R. (2001b). Multiagent planning with factored MDPs. In NIPS-14."},{"key":"9046_CR15","unstructured":"Guestrin, C., Lagoudakis, M., & Parr, R. (2002). Coordinated reinforcement learning. In Proceedings of the 19th International Conference on Machine Learning."},{"key":"9046_CR16","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(89)90049-0","volume":"40","author":"G. Hinton","year":"1986","unstructured":"Hinton G. (1986). Connectionist learning procedures. Artificial Intelligence 40: 185\u2013234","journal-title":"Artificial Intelligence"},{"key":"9046_CR17","unstructured":"Hoen, P., Redekar, H. L. P. G., & Robu, V. (2004). Simulation and visualization of a market-based model for logistics management in transportation. In Proceedings of the Third International Joint Conference on Autonomous Agents and Multi-Agent Systems (pp. 1218\u20131219). New York, NY."},{"key":"9046_CR18","unstructured":"Hu, J., & Wellman, M. P. (1998). Multiagent reinforcement learning: Theoretical framework and an algorithm. In Proceedings of the Fifteenth International Conference on Machine Learning (pp. 242\u2013250)."},{"key":"9046_CR19","volume-title":"Principal component analysis","author":"I. Jolliffe","year":"2002","unstructured":"Jolliffe I. (2002). Principal component analysis (2nd ed). Springer, New York","edition":"2"},{"key":"9046_CR20","unstructured":"Kearns, M., & Koller, D. (1999). Efficient reinforcement learning in factored MDPs. In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (pp. 740\u2013747)."},{"key":"9046_CR21","doi-asserted-by":"crossref","unstructured":"Mataric, M. J. (1998). Coordination and learning in multi-robot systems. In IEEE Intelligent Systems (pp. 6\u20138).","DOI":"10.1109\/5254.671083"},{"issue":"3","key":"9046_CR22","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P. Stone","year":"2000","unstructured":"Stone P. and Veloso M. (2000). Multiagent systems: A survey from a machine learning perspective. Autonomous Robots 8(3): 345\u2013383","journal-title":"Autonomous Robots"},{"key":"9046_CR23","volume-title":"Reinforcement learning: An introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton R.S. and Barto A.G. (1998). Reinforcement learning: An introduction. MIT Press, Cambridge, MA"},{"key":"9046_CR24","unstructured":"Tumer, K. (2005). Designing agent utilities for coordinated, scalable and robust multi-agent systems. In Scerri, P. Mailler, R., & R. Vincent (Eds.), Challenges in the coordination of large scale multiagent Systems. Springer (to appear)."},{"key":"9046_CR25","doi-asserted-by":"crossref","unstructured":"Tumer, K., & Agogino, A. (2007). Distributed agent-based air traffic flow management. In Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multi-Agent Systems (pp. 330\u2013337). Honolulu, HI (Best paper award).","DOI":"10.1145\/1329125.1329434"},{"key":"9046_CR26","doi-asserted-by":"crossref","unstructured":"Tumer, K., Agogino, A., & Wolpert, D. (2002). Learning sequences of actions in collectives of autonomous agents. In Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems, Bologna, Italy (pp. 378\u2013385).","DOI":"10.1145\/544741.544832"},{"key":"9046_CR27","volume-title":"Collectives and the design of complex systems","year":"2004","unstructured":"Tumer K. and Wolpert D. (Eds). (2004a). Collectives and the design of complex systems. Springer, New York"},{"key":"9046_CR28","doi-asserted-by":"crossref","unstructured":"Tumer, K., & Wolpert, D. (2004b). A survey of collectives. In Collectives and the design of complex systems (pp. 1\u201342). Springer.","DOI":"10.1007\/978-1-4419-8909-3_1"},{"key":"9046_CR29","unstructured":"Tumer, K., & Wolpert, D. H. (2000). Collective intelligence and Braess Paradox. In Proceedings of the Seventeeth National Conference on Artificial Intelligence (pp. 104\u2013109)."},{"key":"9046_CR30","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1147\/rd.351.0244","volume":"35","author":"J. Wejchert","year":"1991","unstructured":"Wejchert J. and Tesauro G. (1991). Visualizing processes in neural networks. IBM Journal of Research and Development 35: 244\u2013253","journal-title":"IBM Journal of Research and Development"},{"issue":"2\/3","key":"9046_CR31","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1142\/S0219525901000188","volume":"4","author":"D.H. Wolpert","year":"2001","unstructured":"Wolpert D.H. and Tumer K. (2001). Optimal payoff functions for members of collectives. Advances in Complex Systems 4(2\/3): 265\u2013279","journal-title":"Advances in Complex Systems"},{"key":"9046_CR32","doi-asserted-by":"crossref","first-page":"017701","DOI":"10.1103\/PhysRevE.69.017701","volume":"69","author":"D.H. Wolpert","year":"2004","unstructured":"Wolpert D.H., Tumer K. and Bandari E. (2004). Improving search algorithms by using intelligent coordinates. Physical Review E 69: 017701","journal-title":"Physical Review E"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-008-9046-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-008-9046-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-008-9046-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,25]],"date-time":"2024-02-25T10:29:33Z","timestamp":1708856973000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-008-9046-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,4,23]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2008,10]]}},"alternative-id":["9046"],"URL":"https:\/\/doi.org\/10.1007\/s10458-008-9046-9","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,4,23]]}}}