{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,18]],"date-time":"2025-05-18T04:03:21Z","timestamp":1747541001091,"version":"3.40.5"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2003,5,1]],"date-time":"2003-05-01T00:00:00Z","timestamp":1051747200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2003,5,1]],"date-time":"2003-05-01T00:00:00Z","timestamp":1051747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Autonomous Agents and Multi-Agent Systems"],"published-print":{"date-parts":[[2003,5]]},"DOI":"10.1023\/a:1022935725296","type":"journal-article","created":{"date-parts":[[2003,4,7]],"date-time":"2003-04-07T22:16:51Z","timestamp":1049753811000},"page":"287-316","source":"Crossref","is-referenced-by-count":11,"title":["Maximizing Reward in a Non-Stationary Mobile Robot Environment"],"prefix":"10.1007","volume":"6","author":[{"given":"Dani","family":"Goldberg","sequence":"first","affiliation":[]},{"given":"Maja J.","family":"Matari\u0107","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"5118226_CR1","volume-title":"Behavior-Based Robotics","author":"R. C. Arkin","year":"1998","unstructured":"R. C. Arkin, Behavior-Based Robotics, The MIT Press: Cambridge, Massachusetts, 1998."},{"key":"5118226_CR2","doi-asserted-by":"crossref","unstructured":"R. C. Arkin and K. S. Ali, \u201cReactive and Telerobotic Control in Multi-Agent Systems, \u201d in From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adpative Behavior, Brighton, England, pp. 473\u2013478, 1994.","DOI":"10.7551\/mitpress\/3117.003.0067"},{"key":"5118226_CR3","doi-asserted-by":"crossref","unstructured":"R. C. Arkin, T. Balch, and E. Nitz, \u201cCommunication of Behavioral State in Multi-Agent Retrieval Tasks, \u201d in IEEE International Conference on Robotics and Automation, Atlanta, pp. 588\u2013594, 1993.","DOI":"10.1109\/ROBOT.1993.291841"},{"key":"5118226_CR4","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1023\/A:1008973424594","volume":"8","author":"T. Balch","year":"2000","unstructured":"T. Balch, \u201cHierarchical Social Entropy: An Information Theoretic Measure of Robot Group Diversity, \u201d Autonomous Robots, vol. 8, pp. 209\u2013237, 2000.","journal-title":"Autonomous Robots"},{"key":"5118226_CR5","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/0004-3702(94)00005-L","volume":"72","author":"R. D. Beer","year":"1993","unstructured":"R. D. Beer, \u201cA Dynamical Systems Perspective on Agent-Environment Interaction, \u201d Artificial Intelligence, vol. 72, pp. 173\u2013215, 1993.","journal-title":"Artificial Intelligence"},{"key":"5118226_CR6","doi-asserted-by":"crossref","unstructured":"R. A. Brooks, \u201cThe Behavior Language: User's Guide, \u201d Technical Report AIM-1227, MIT AI Laboratory 1990.","DOI":"10.21236\/ADA225808"},{"key":"5118226_CR7","unstructured":"R. A. Brooks, \u201cIntelligence Without Reason, \u201d in Proceedings of the Twelfth International Joint Conference on Artificial Intelligence (IJCAI-91), Sydney, Australia, pp. 569\u2013590, 1991."},{"issue":"395","key":"5118226_CR8","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1080\/01621459.1986.10478343","volume":"81","author":"C. R. Blyth","year":"1986","unstructured":"C. R. Blyth, \u201cApproximate Binomial Confidence Limits, \u201d Journal of the American Statistical Association, vol. 81, no.395, pp. 843\u2013855, 1986.","journal-title":"Journal of the American Statistical Association"},{"key":"5118226_CR9","first-page":"1","volume":"4","author":"Y. U. Cao","year":"1997","unstructured":"Y. U. Cao, A. S. Fukunaga, and A. B. Kahng, \u201cCooperative Mobile Robotics: Antecedents and Directions, \u201d Autonomous Robots, vol. 4, pp. 1\u201323, 1997.","journal-title":"Autonomous Robots"},{"key":"5118226_CR10","first-page":"963","volume":"2","author":"A. R. Cassandra","year":"1996","unstructured":"A. R. Cassandra, L. P. Kaelbling, and J. A. Kurien, \u201cActing under Uncertainty: Discrete Bayesian Models for Mobile-Robot Navigation, \u201d in Proceedings of the 1996 IEEE\/RSJ International Conference on Intelligent Robots and Systems, vol. 2, pp. 963\u2013972, 1996.","journal-title":"Proceedings of the 1996 IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"issue":"3","key":"5118226_CR11","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1214\/aoms\/1177700517","volume":"35","author":"H. Chernoff","year":"1964","unstructured":"H. Chernoff and S. Zacks, \u201cEstimating the Current Mean of a Normal Distribution which is Subjected to Changes in Time, \u201d Annals of Mathematical Statistics, vol. 35, no.3, pp. 999\u20131018, 1964.","journal-title":"Annals of Mathematical Statistics"},{"key":"5118226_CR12","unstructured":"T. H. Cormen, C. E. Leiserson, and R. L. Rivest, Introduction to Algorithms, McGraw-Hill Book Company, 1990."},{"key":"5118226_CR13","unstructured":"L. Chrisman, \u201cReinforcement Learning with Perceptual Aliasing: The Perceptual Distinctions Approach, \u201d in W. Swartout (ed.), Proceedings of the 10th National Conference on Artificial Intelligence, San Jose, CA, pp. 183\u2013188, 1992."},{"issue":"5","key":"5118226_CR14","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1109\/70.720357","volume":"14","author":"M. S. Font\u00e1n","year":"1998","unstructured":"M. S. Font\u00e1n and M. J. Matari\u00b4c, \u201cTerritorial Multi-Robot Task Division, \u201d IEEE Transactions on Robotics and Automation, vol. 14, no.5, pp. 815\u2013822, 1998.","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"5118226_CR15","unstructured":"J. E. Freund, Mathematical Statistics, Fifth Edition, Prentice Hall, 1992."},{"key":"5118226_CR16","unstructured":"E. Gat, \u201cOn Three-Layer Architectures, \u201d in D. Kortenkamp, R. P. Bonnasso, and R. Murphy (eds.), Artificial Intelligence and Mobile Robotics: Case Studies of Successful Robot Systems, AAAI Press, pp. 195\u2013210, 1998."},{"key":"5118226_CR17","unstructured":"D. Goldberg, \u201cEvaluating the Dynamics of Agent Environment Interaction, \u201d Ph.D. thesis, University of Southern California, 2001."},{"key":"5118226_CR18","doi-asserted-by":"crossref","unstructured":"D. Goldberg and M. J. Matari\u0107, \u201cCoordinating Mobile Robot Group Behavior Using a Model of Interaction Dynamics, \u201d in Proceedings, The Third International Conference on Autonomous Agents (Agents' 99), Seattle, Washington, pp. 100\u2013107, 1999.","DOI":"10.1145\/301136.301172"},{"key":"5118226_CR19","doi-asserted-by":"crossref","unstructured":"D. Goldberg and M. J. Matari\u0107, \u201cDetecting Regime Changes with a Mobile Robot using Multiple Models, \u201d in Proceedings of the 2001 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Maui, Hawaii, pp. 619\u2013624, 2001.","DOI":"10.1109\/IROS.2001.976238"},{"key":"5118226_CR20","doi-asserted-by":"crossref","unstructured":"K. Han and M. Veloso, \u201cAutomated Robot Behavior Recognition Applied to Robotic Soccer, \u201d in Robotics Research: the Ninth International Symposium, Snowbird, Utah, pp. 249\u2013256, 2000.","DOI":"10.1007\/978-1-4471-0765-1_30"},{"key":"5118226_CR21","unstructured":"S. J. Hanson, \u201cMeiosis Networks, \u201d in D. S. Touretzky (ed.), Advances in Neural Information Processing Systems 2, San Mateo, CA, pp. 533\u2013541, 1990."},{"issue":"1\u20132","key":"5118226_CR22","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"L. P. Kaelbling","year":"1998","unstructured":"L. P. Kaelbling, M. L. Littman, and A. R. Cassandra, \u201cPlanning and Acting in Partially Observable Stochastic Domains, \u201d Artificial Intelligence, vol. 101, no.1\u20132, pp. 99\u2013134, 1998.","journal-title":"Artificial Intelligence"},{"key":"5118226_CR23","unstructured":"J. G. Kemeny, J. L. Snell, and A. W. Knapp, Denumerable Markov Chains, D. Van Nostrand Company, Inc., 1966."},{"key":"5118226_CR24","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1109\/ROBOT.1996.506507","volume":"3","author":"S. Koenig","year":"1996","unstructured":"S. Koenig and R. G. Simmons, \u201cUnsupervised Learning of Probabilistic Models for Robot Navigation, \u201d in Proceedings of the IEEE International Conference on Robotics and Automation, vol. 3, pp. 2301\u20132308, 1996.","journal-title":"Proceedings of the IEEE International Conference on Robotics and Automation"},{"key":"5118226_CR25","unstructured":"J. Ko\u0161eck\u00e1 and R. Bajcsy, \u201cDiscrete Event Systems for Autonomous Mobile Agents, \u201d in Proceedings of the First Workshop on Intelligent Robotic Systems, Zakopane, Poland, pp. 21\u201331, 1993."},{"issue":"4","key":"5118226_CR26","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1111\/j.2517-6161.1995.tb02052.x","volume":"57","author":"T. L. Lai","year":"1995","unstructured":"T. L. Lai, \u201cSequential Changepoint Detection in Quality Control and Dynamical Systems, \u201d Journal of the Royal Statistical Society, Series B (Methodological), vol. 57, no.4, pp. 613\u2013658, 1995.","journal-title":"Journal of the Royal Statistical Society, Series B (Methodological)"},{"issue":"362","key":"5118226_CR27","first-page":"274","volume":"73","author":"R. F. Ling","year":"1978","unstructured":"R. F. Ling \u201cA Study of the Accuracy of Some Approximations for t, \u03c7\n2, and F Tail Probabilities, \u201d Journal of the American Statistical Association, vol. 73, no.362, pp. 274\u2013283, 1978.","journal-title":"Journal of the American Statistical Association"},{"key":"5118226_CR28","unstructured":"S. Mahadevan and G. Theocharous, \u201cOptimizing Production Manufacturing using Reinforcement Learning, \u201d in Proceedings of the Eleventh International FLAIRS Conference, Sanibel Island, Florida, pp. 372\u2013377, 1998."},{"key":"5118226_CR29","unstructured":"M. J. Matari\u0107, \u201cBehavior-Based Systems: Key Properties and Implications, \u201d in IEEE International Conference on Robotics and Automation, Workshop on Architectures for Intelligent Control Systems, Nice, France, pp. 46\u201354, 1992."},{"issue":"2\u20134","key":"5118226_CR30","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/0921-8890(95)00053-4","volume":"16","author":"M. J. Matari\u0107","year":"1995","unstructured":"M. J. Matari\u0107, \u201cIssues and Approaches in the Design of Collective Autonomous Agents, \u201d Robotics and Autonomous Systems, vol. 16, no.2\u20134, pp. 321\u2013331, 1995.","journal-title":"Robotics and Autonomous Systems"},{"issue":"2\u20133","key":"5118226_CR31","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1080\/095281397147149","volume":"9","author":"M. J. Matari\u0107","year":"1997","unstructured":"M. J. Matari\u0107, \u201cBehavior-Based Control: Examples from Navigation, Learning, and Group Behavior, \u201d Journal of Experimental and Theoretical Artificial Intelligence, vol. 9, no.2\u20133, pp. 323\u2013336, 1997.","journal-title":"Journal of Experimental and Theoretical Artificial Intelligence"},{"key":"5118226_CR32","unstructured":"A. K. McCallum, \u201cReinforcement Learning with Selective Perception and Hidden State, \u201d Ph.D. thesis, University of Rochester, Department of Computer Science, 1996."},{"issue":"3\u20134","key":"5118226_CR33","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1023\/A:1008814507256","volume":"5","author":"F. Michaud","year":"1998","unstructured":"F. Michaud and M. J. Matari\u0107, \u201cLearning from History for Behavior-Based Mobile Robots in Nonstationary Conditions, \u201d Autonomous Robots, vol. 5, no.3\u20134, pp. 335\u2013354, 1998.","journal-title":"Autonomous Robots"},{"key":"5118226_CR34","unstructured":"T. M. Mitchell, Machine Learning, The McGraw-Hill Companies, Inc., 1997."},{"key":"5118226_CR35","unstructured":"L. E. Parker, \u201cHeterogeneous Multi-Robot Cooperation, \u201d Ph.D. thesis, MIT, 1994."},{"issue":"324","key":"5118226_CR36","first-page":"1416","volume":"63","author":"D. B. Peizer","year":"1968","unstructured":"D. B. Peizer and J. W. Pratt, \u201cA Normal Approximation for Binomial, F, Beta, and Other Common, Related Tail Probabilities, 1, \u201d Journal of the American Statistical Association, vol. 63, no.324, pp. 1416\u20131456, 1968.","journal-title":"Journal of the American Statistical Association"},{"key":"5118226_CR37","volume-title":"Multiple Objective Action Selection & Behavior Fusion using Voting","author":"P. Pirjanian","year":"1998","unstructured":"P. Pirjanian, \u201cMultiple Objective Action Selection & Behavior Fusion using Voting, \u201d Ph.D. thesis, Institute of Electronic Systems, Alborg University, Denmark, 1998."},{"key":"5118226_CR38","unstructured":"W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery, Numerical Recipes in C: The Art of Scientific Computing, Cambridge University Press, 1992."},{"issue":"2","key":"5118226_CR39","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L. R. Rabiner","year":"1989","unstructured":"L. R. Rabiner, \u201cA Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, \u201d Proceedings of the IEEE, vol. 77, no.2, pp. 257\u2013285, 1989.","journal-title":"Proceedings of the IEEE"},{"key":"5118226_CR40","unstructured":"F. S. Roberts, Discrete Mathematical Models: With Applications to Social, Biological, and Environmental Problems, Prentice-Hall, Inc., 1976."},{"key":"5118226_CR41","volume-title":"Applied Probability Models with Optimization Applications","author":"S. M. Ross","year":"1992","unstructured":"S. M. Ross, Applied Probability Models with Optimization Applications, New York: Dover Publications, Inc., 1992."},{"key":"5118226_CR42","unstructured":"K. Seymore, A. McCallum, and R. Rosenfeld, \u201cLearning Hidden Markov Model Structure for Information Extraction, \u201d in Proceedings of the Sixteenth National Conference on Artificial Intelligence: Workshop on Machine Learning for Information Extraction, Orlando, FL, pp. 37\u201342, 1999."},{"key":"5118226_CR43","doi-asserted-by":"crossref","unstructured":"T. Smithers, \u201cWhat the Dynamics of Adaptive Behavior and Cognition Might Look Like in Agent-Environment Interaction Systems, \u201d in Practice and Future of Autonomous Agents, Mt. Verita, Switzerland, 1995.","DOI":"10.1049\/ic:19951350"},{"key":"5118226_CR44","unstructured":"A. Stolcke and S. Omohundro, \u201cHidden Markov Model Induction by Bayesian Model Merging, \u201d in S. J. Hanson, J. D. Cowan, and C. L. Giles (eds.), Advances in Neural Information Processing Systems, vol. 5. pp. 11\u201318, 1993."},{"key":"5118226_CR45","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. S. Sutton","year":"1999","unstructured":"R. S. Sutton, D. Precup, and S. Singh, \u201cBetween MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning, \u201d Artificial Intelligence, vol. 112, pp. 181\u2013211, 1999.","journal-title":"Artificial Intelligence"},{"key":"5118226_CR46","unstructured":"G. Wang and S. Mahadevan, \u201cHierarchical Optimization of Policy-Coupled Semi-Markov Decision Processes, \u201d in Proceedings of the Sixteenth International Conference on Machine Learning, Bled, Slovenia, pp. 464\u2013473, 1999."},{"issue":"1\u20132","key":"5118226_CR47","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/0004-3702(94)00012-P","volume":"73","author":"S. D. Whitehead","year":"1995","unstructured":"S. D. Whitehead and L.-J. Lin, \u201cReinforcement Learning of Non-Markov Decision Processes, \u201d Artificial Intelligence, vol. 73, no.1\u20132, pp. 271\u2013306, 1995.","journal-title":"Artificial Intelligence"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1022935725296.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1022935725296\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1022935725296.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T06:10:19Z","timestamp":1747462219000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1022935725296"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,5]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2003,5]]}},"alternative-id":["5118226"],"URL":"https:\/\/doi.org\/10.1023\/a:1022935725296","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"type":"print","value":"1387-2532"},{"type":"electronic","value":"1573-7454"}],"subject":[],"published":{"date-parts":[[2003,5]]}}}