{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T13:47:55Z","timestamp":1786110475232,"version":"3.56.0"},"reference-count":91,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2003,10,1]],"date-time":"2003-10-01T00:00:00Z","timestamp":1064966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2003,10,1]],"date-time":"2003-10-01T00:00:00Z","timestamp":1064966400000},"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":["Discrete Event Dynamic Systems"],"published-print":{"date-parts":[[2003,10]]},"DOI":"10.1023\/a:1025696116075","type":"journal-article","created":{"date-parts":[[2003,9,23]],"date-time":"2003-09-23T18:47:08Z","timestamp":1064342828000},"page":"341-379","source":"Crossref","is-referenced-by-count":308,"title":["Recent Advances in Hierarchical Reinforcement Learning"],"prefix":"10.1007","volume":"13","author":[{"given":"Andrew G.","family":"Barto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sridhar","family":"Mahadevan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"5144388_CR1","first-page":"1019","volume-title":"Advances in Neural Information Processing Svstesns: Proceedings of the 2000 Conference","author":"D. Andre","year":"2001","unstructured":"Andre, D., and Russell, S. J. 2001. Programmable reinforcement learning agents. In Advances in Neural Information Processing Svstesns: Proceedings of the 2000 Conference. Cambridge, MA: MIT Press, pp. 1019-1025."},{"key":"5144388_CR2","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/0004-3702(94)00011-O","volume":"72","author":"A. G. Barto","year":"1995","unstructured":"Barto, A. G., Bradike, S. J., and Singh. S. P. 1995. Learning to act using real-time dynamic programming. Artificial Intelligence 72: 81-138.","journal-title":"Artificial Intelligence"},{"key":"5144388_CR3","first-page":"32","volume-title":"Uncertainly in Artificial Intelligence: Proceedings of the 16th Conference","author":"D. Bemstein","year":"2000","unstructured":"Bemstein, D., Zilberstein, S., and Immerman, N. 2000. The complexity of decentralized control of markov decision processes. In C. Boutilier and M. Goldszmidt (eds). Uncertainly in Artificial Intelligence: Proceedings of the 16th Conference. San Francisco CA: Morgan Kaufmann, pp. 32-37."},{"key":"5144388_CR4","volume-title":"Dynamic Programming: Deterministic and Stochastic Models","author":"D. P. Bertsekas","year":"1987","unstructured":"Bertsekas, D. P. 1987. Dynamic Programming: Deterministic and Stochastic Models. Englewood Cliffs, NJ: Prentice-Hall."},{"key":"5144388_CR5","volume-title":"Neuro-Dynamic Programming","author":"D. P. Bertsekas","year":"1996","unstructured":"Bertsekas, D. P., and Tsitsiklis, J. N. 1996. Neuro-Dynamic Programming. Belmont, MA: Athena Scientific."},{"key":"5144388_CR6","first-page":"33","volume-title":"Proceedings of the Fourteenth Conference on Uncertainty in Al","author":"X. Boyen","year":"1998","unstructured":"Boyen, X., and Koller, D. 1998. Tractable inference for complex stochastic processes. In G. F Cooper and S. Moral (eds.), Proceedings of the Fourteenth Conference on Uncertainty in Al, San Francisco. CA: Morgan Kaufmann, pp. 33-42."},{"key":"5144388_CR7","first-page":"393","volume-title":"Advances in Neural Information Processing Systems: Proceedings of the 1994 Conference","author":"S. J. Bradtke","year":"1995","unstructured":"Bradtke, S. J., and Duff. M. O. 1995. Reinforcement learning methods for continuous-time markov decision problems. In G. Tesauro. D. S. Touretzky and T. Leen (eds.). Advances in Neural Information Processing Systems: Proceedings of the 1994 Conference. Cambridge. MA: MIT Press. pp. 393-400."},{"key":"5144388_CR8","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/9.654885","volume":"43","author":"M. S. Branicky","year":"1998","unstructured":"Branicky, M. S., Borkar, V. S., and Mitter, S. K. 1998. A unified framework for hybnd control: Model and optimal control theory. IEEE Transactions on Automatic Control 43: 31-45.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"5144388_CR9","volume-title":"Achieving artificial intelligence through building robots. Technical Report Al. Memo 899","author":"R. A. Brooks","year":"1986","unstructured":"Brooks, R. A. 1986. Achieving artificial intelligence through building robots. Technical Report Al. Memo 899. Cambridge, MA: Massachusetts Institute of Technology Artificial Intelligence Laboratory."},{"key":"5144388_CR10","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1016\/S0005-1098(01)00282-5","volume":"38","author":"X. R. Cao","year":"2002","unstructured":"Cao, X. R., Ren, Z., Bhatnagar, S., Fu, M., and Marcus, S. 2002. A time aggregation approach to Markov decision processes. Automatica 38: 929-943.","journal-title":"Automatica"},{"key":"5144388_CR11","volume-title":"Large-Scale Dvnaniic Optimization Using Teams of Reinforcement Learning Agents","author":"R. H. Crites","year":"1996","unstructured":"Crites. R. H. 1996. Large-Scale Dvnaniic Optimization Using Teams of Reinforcement Learning Agents. Ph.D. thesis. Amherst. MA: University of Massachusetts."},{"key":"5144388_CR12","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1007518724497","volume":"33","author":"R. H. Crites","year":"1998","unstructured":"Crites. R. H., and Barto. A. G. 1998. Elevator group control using multiple reinforcement learning agents. Machine Learning 33: 235-262.","journal-title":"Machine Learning"},{"key":"5144388_CR13","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1287\/mnsc.45.4.560","volume":"45","author":"T. K. Das","year":"1999","unstructured":"Das. T. K., Gosavi. A., Mahadevan, S., and Marchalleck, N. 1999. Solving semi-Markov decision problems using average reward reinforcement learning. Management Science 45: 560-574.","journal-title":"Management Science"},{"key":"5144388_CR14","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1111\/j.1467-8640.1989.tb00324.x","volume":"5","author":"T. L. Dean","year":"1989","unstructured":"Dean. T. L., and Kanazawa, K. 1989. A model for reasoning about persistence and causation. Computational Intelligence 5: 142-150.","journal-title":"Computational Intelligence"},{"key":"5144388_CR15","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"T. G. Dietterich","year":"2000","unstructured":"Dietterich, T. G. 2000. Hierarchical reinforcement learning with the maxq value function decomposition. Journal of Artificial intelligence Research 13: 227-303.","journal-title":"Journal of Artificial intelligence Research"},{"key":"5144388_CR16","volume-title":"From Animals to Animals 4: The Fourth Confe,-ence on Simulation of Adaptive Behavior","author":"B. Digney","year":"1996","unstructured":"Digney, B. 1996. Emergent hierarchical control structures: Learning reactive\/hierarchical relationships in reinforcement environments. In P. Meas and M. Mataric (eds.), From Animals to Animals 4: The Fourth Confe,-ence on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press."},{"key":"5144388_CR17","volume-title":"From Animals to Animals 5: The Fifth Conference on Simulation of Adaptive Behavior","author":"B. Digney","year":"1998","unstructured":"Digney, B. 1998. Learning hierarchical control structure from multiple tasks and changing environments. In From Animals to Animals 5: The Fifth Conference on Simulation of Adaptive Behavior. Carnbndge, MA: MIT Press."},{"key":"5144388_CR18","first-page":"115","volume-title":"Maching Learning: Proceedings of the Nineteenth international Conference on Machine Learning","author":"K. Driessens","year":"2002","unstructured":"Driessens, K., and Dzeroski, S. 2002. Integrating experimentation and guidance in relational reinforcement learning. In Maching Learning: Proceedings of the Nineteenth international Conference on Machine Learning. San Francisco. GA: Morgan Kaufmann. pp. 115-122."},{"key":"5144388_CR19","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0004-3702(72)90051-3","volume":"3","author":"R. E. Fikes","year":"1972","unstructured":"Fikes. R. E., Hart, P. E., and Nilsson, N. J. 1972. Learning and executing generalized robot plans. Artificial Intelligence 3:251-288.","journal-title":"Artificial Intelligence"},{"key":"5144388_CR20","doi-asserted-by":"crossref","unstructured":"Fine, S., Singer, Y., and Tishby, N. 1998. The hierarchical hidden Markov model: analysis and applications. Machine Learning 32(1). July.","DOI":"10.1023\/A:1007469218079"},{"key":"5144388_CR21","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/TAC.1978.1101707","volume":"AC-23","author":"J.-P. Forestier","year":"1978","unstructured":"Forestier, J.-P., and Varaiya, P. 1978. Multilayer control of large markov chains. IEEE Transactions on Automatic Control AC-23: 298-304.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"5144388_CR22","first-page":"186","volume-title":"Proceedings of the Eighteenth International conference on Machine Learning","author":"M. Ghavarnzadeh","year":"2001","unstructured":"Ghavarnzadeh, M., and Mahadevan, S. 2001. Continuous-time hierarchical reinforcement learning. In Proceedings of the Eighteenth International conference on Machine Learning. San Francisco. CA: Morgan Kaufmann, pp. 186-193."},{"key":"5144388_CR23","first-page":"195","volume-title":"Proceedings of the Ni,ieteenth i,iternatioiial conference on Machine Learning (1LML 2002)","author":"M. Ghavamzadeh","year":"2002","unstructured":"Ghavamzadeh, M., and Mahadevan, S. 2002. Hierarchically optimal average reward reinforcement learning. In C. Sammut and M. Goldszmidt (eds). Proceedings of the Ni,ieteenth i,iternatioiial conference on Machine Learning (1LML 2002). San Francisco CA: Morgan Kaufmann, pp. 195-202."},{"key":"5144388_CR24","unstructured":"Grudic. G. Z., and Ungar. L. H. 2000. Localizing search in reinforcement learning. In Proceedings of the 18th National Conference on Artificial Intelligence, (AAAI-00), pp. 590-595."},{"key":"5144388_CR25","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/0167-6423(87)90035-9","volume":"8","author":"D. Harel","year":"1987","unstructured":"Harel, D. 1987. Statecharts: Avisual formalixm for complex systems. Science of Coniputer Programming 8: 231-274.","journal-title":"Science of Coniputer Programming"},{"key":"5144388_CR26","first-page":"243","volume-title":"Maching Learning: Proceedings of the Nineteenth International Conference on Machine Learning","author":"B. Hengst","year":"2002","unstructured":"Hengst, B. 2002. Discovering hierarchy in reinforcement learning with hexq. In Maching Learning: Proceedings of the Nineteenth International Conference on Machine Learning. San Francisco, CA: Morgan Kaufmann, pp. 243-250."},{"key":"5144388_CR27","first-page":"1047","volume-title":"Advances in Neural information Processing Systems: Proceedings of the 2000 conference","author":"N. Hernandez","year":"2001","unstructured":"Hernandez, N., and Mahadevan. S. 2001. Hierarchical memory-based reinforcement learning. In Advances in Neural information Processing Systems: Proceedings of the 2000 conference. Cambridge, MA: MIT Press, pp. 1047-1053."},{"key":"5144388_CR28","volume-title":"Dynamic Probabilistic Systems: Semi-Markar and Decision Processes","author":"R. A. Howard","year":"1971","unstructured":"Howard, R. A. 1971. Dynamic Probabilistic Systems: Semi-Markar and Decision Processes. New York: Wiley."},{"key":"5144388_CR29","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/S0921-8890(97)00044-4","volume":"22","author":"M. Huber","year":"1997","unstructured":"Huber, M., and Grupen. R. A. 1997. A feedback control structure for on-line learning tasks. Robotics and Autononioiis Sstems 22: 303-315.","journal-title":"Robotics and Autononioiis Sstems"},{"key":"5144388_CR30","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1023\/A:1022693717366","volume":"3","author":"G. A. Iba","year":"1989","unstructured":"Iba, G. A. 1989. A heuristic approach to the discovery of macro-operators. Machine Learning 3: 285-317.","journal-title":"Machine Learning"},{"key":"5144388_CR31","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1162\/neco.1994.6.6.1185","volume":"6","author":"T. Jaakkola","year":"1994","unstructured":"Jaakkola, T., Jordan, M. I., and Singh, S. P. 1994. On the convergence of stochastic iterative dynamic programming algorithms. Neural Computation 6: 1185-1201.","journal-title":"Neural Computation"},{"key":"5144388_CR32","first-page":"1054","volume-title":"Advances in Neural Information Processing Systems: Proceedings of the 2000 Conference","author":"A. Jonsson","year":"2001","unstructured":"Jonsson. A., and Barto. A. G. 2001. Automated state abstraction for options using the li-tree algorithm. In Advances in Neural Information Processing Systems: Proceedings of the 2000 Conference. Cambridge, MA: MIT Press, pp. 1054-1060."},{"key":"5144388_CR33","doi-asserted-by":"crossref","unstructured":"Kaelbling, L., Littrnan. M., and Cassandra, A. 1998. Planning and acting in partially observable stochastic domains. Artificial intelligence 101.","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"5144388_CR34","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L. P. Kaelbling","year":"1996","unstructured":"Kaelbling, L. P., Littman, M. L., and Moore, A. W. 1996. Reinforcement learning: A survey. Journal of Artificial Intelligence Research 4: 237-285.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"5144388_CR35","series-title":"Technical Report","volume-title":"Brain function and adaptive systems-a heterostatic theory","author":"A. H. Klopf","year":"1972","unstructured":"Klopf, A. H. 1972. Brain function and adaptive systems-a heterostatic theory. Technical Report AFCRL-72-0164, Bedford, MA: Air Force Cambridge Research Laboratories. A summary appears in Proceedings of the International Conference on Systems,Man, and Cybernetics, 1974, IEEE Systems, Man, and Cybernetics Society, Dallas, TX."},{"key":"5144388_CR36","volume-title":"The Hedonistic Neuron: A Theory of Memory, Learning, and Intelligence","author":"A. H. Klopf","year":"1982","unstructured":"Klopf, A. H. 1982. The Hedonistic Neuron: A Theory of Memory, Learning, and Intelligence. Washington, D.C.: Hemisphere."},{"key":"5144388_CR37","volume-title":"Al-based Mobile Robots: Case-studies of Successful Robot Systems","author":"S. Koenig","year":"1997","unstructured":"Koenig, S., and Simmons, R. 1997. Xavier: A robot navigation architecture based on partially observable markov decision process models. In D. Kortenkamp, P. Bonasso, and R. Murphy (eds.), Al-based Mobile Robots: Case-studies of Successful Robot Systems. Cambridge, MA: MIT Press."},{"key":"5144388_CR38","volume-title":"Singular Perturbation Methods in Control: Analysis and Design","author":"P. V. Kokotovic","year":"1986","unstructured":"Kokotovic, P. V., Khalil, H. K., and O'Reilly, J. 1986. Singular Perturbation Methods in Control: Analysis and Design. London: Academic Press."},{"key":"5144388_CR39","volume-title":"Learning to Solve Problems by Searching for Macro-Operators","author":"R. E. Korf","year":"1985","unstructured":"Korf, R. E. 1985. Learning to Solve Problems by Searching for Macro-Operators. Boston, MA: Pitman."},{"key":"5144388_CR40","first-page":"157","volume-title":"Proceedings of the Eleventh International Conference on Machine Learning","author":"M. Littman","year":"1994","unstructured":"Littman. M. 1994. Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the Eleventh International Conference on Machine Learning. San Francisco, CA: Morgan Kaufmann, pp. 157-163."},{"key":"5144388_CR41","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1023\/A:1018064306595","volume":"22","author":"S. Mahadevan","year":"1996","unstructured":"Mahadevan, S. 1996. Average reward reinforcement leaming: Foundations, algorithms, and empirical results. Machine Learning 22: 159-196.","journal-title":"Machine Learning"},{"key":"5144388_CR42","first-page":"202","volume-title":"Proceedings of the Fourteenth international Conference","author":"S. Mahadevan","year":"1997","unstructured":"Mahadevan, S., Marchalleck, N., Das, T., and Gosavi, A. 1997. Self-improving factory simulation using continuous-time average-reward reinforcement learning. In Proceedings of the Fourteenth international Conference. San Francisco, CA: Morgan Kaufmann, pp. 202-210."},{"key":"5144388_CR43","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1145\/375735.376302","volume-title":"Proceedings of the Fifth international Conference on Autonomous Agents","author":"R. Makar","year":"2001","unstructured":"Makar, R., Mahadevan, S., and Ghavamzadeh, M. 2001. Hierarchical multi-agent reinforcement learning. In J. P. Muller, E. Andre, S. Sen, and C. Frasson (eds.), Proceedings of the Fifth international Conference on Autonomous Agents. New York: ACM Press, pp. 246-253."},{"key":"5144388_CR44","unstructured":"McCalIum, A. K. 1996. Reinforcement Learning with Selective Perceptioin and Hidden State. Ph.D. thesis, University of Rochester."},{"key":"5144388_CR45","doi-asserted-by":"crossref","unstructured":"McGovern, A. 2002. Autonomous Discovers of Temporal Abstractions from interaction with An Environment. Ph.D. thesis. University of Massachusetts.","DOI":"10.1007\/3-540-45622-8_34"},{"key":"5144388_CR46","first-page":"361","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning","author":"A. McGovern","year":"2001","unstructured":"McGovern, A., and Barb, A. 2001. Automatic discovery of subgoals in reinforcement learning using diverse density. In Proceedings of the Eighteenth International Conference on Machine Learning. San Francisco, CA: Morgan Kaufmann, pp. 361-368."},{"key":"5144388_CR47","unstructured":"Minsky, M. L. 1954. Theory of Neural-Analog Reinforcement Systems and its Application to the Brain-Model Problem. Ph.D. thesis, Princeton University."},{"key":"5144388_CR48","doi-asserted-by":"crossref","DOI":"10.1049\/PBCE034E","volume-title":"Singular Perturbation Methodology in Control Systems","author":"D. S. Naidu","year":"1988","unstructured":"Naidu, D. S. 1988. Singular Perturbation Methodology in Control Systems. London: Peter Peregrinus Ltd."},{"issue":"2","key":"5144388_CR49","first-page":"53","volume":"16","author":"I. Nourbakhsh","year":"1995","unstructured":"Nourbakhsh, I., Powers, R., and Birchfield, S. 1995. Dervish: An office-navigation robot. Al Magazine 16(2): 53-60.","journal-title":"Al Magazine"},{"key":"5144388_CR50","volume-title":"Hierarchical Control and Learning for Markov Decision Processes","author":"R. Parr","year":"1998","unstructured":"Parr, R. 1998. Hierarchical Control and Learning for Markov Decision Processes. PhD thesis, Berkeley, CA: University of California."},{"key":"5144388_CR51","volume-title":"Advances in Neural information Processing Systems: Proceedings of the 1997 Conference","author":"R. Parr","year":"1998","unstructured":"Parr, R., and Russell, S. 1998. Reinforcement learning with hierarchies of machines. In Advances in Neural information Processing Systems: Proceedings of the 1997 Conference. Cambridge. MA: MIT Press."},{"key":"5144388_CR52","first-page":"409","volume-title":"Proceedings of the Eighteenth international Conference on Machine Learning","author":"T. J. Perkins","year":"2001","unstructured":"Perkins, T. J., and Barto, A. G. 2001. Lyapunov-constrained action sets for reinforcement learning. In C. Brodley and A. Danyluk (eds.). Proceedings of the Eighteenth international Conference on Machine Learning.San Francisco, CA: Morgan Kaufmann. pp. 409-416."},{"key":"5144388_CR53","first-page":"803","volume":"3","author":"T. J. Perkins","year":"2002","unstructured":"Perkins, T. J., and Barb, A. G. 2002. Lyapunov design for safe reinforcement learning. Journal of Machine Learning Research 3: 803-832.","journal-title":"Journal of Machine Learning Research"},{"key":"5144388_CR54","volume-title":"Temporal Abstraction in Reinforcentent Learning","author":"D. Precup","year":"2000","unstructured":"Precup, D. 2000. Temporal Abstraction in Reinforcentent Learning. Ph.D. thesis, Amherst, MA: University of Massachusetts."},{"key":"5144388_CR55","first-page":"1050","volume-title":"Advances in Neural information Processing Systems: Proceedings of the 1997 Conference","author":"D. Precup","year":"1998","unstructured":"Precup. D., and Sutton, R. S. 1998. Multi-time models for temporally abstract planning. In Advances in Neural information Processing Systems: Proceedings of the 1997 Conference. Cambridge MA: MIT Press, pp. 1050-1056."},{"key":"5144388_CR56","doi-asserted-by":"crossref","unstructured":"Precup. D., Sutton, R. S., and Singh, S. 1998. Theoretical results on reinforcement learning with temporally abstract options. In Proceedings of the 10th European Conference on Machime Learning, ECML-98. Springer Verlag, pp. 382-393.","DOI":"10.1007\/BFb0026709"},{"key":"5144388_CR57","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Problems","author":"M. L. Puterman","year":"1994","unstructured":"Puterman, M. L. 1994. Markov Decision Problems. Wiley, NY."},{"key":"5144388_CR58","volume-title":"Advances in Neural Information Processing Systems: Proceedings of the 2002 Conference","author":"K. Rohanimanesh","year":"2002","unstructured":"Rohanimanesh, K., and Mahadevan, S. 2002 Learning to take concurrent actions. In Advances in Neural Information Processing Systems: Proceedings of the 2002 Conference. Cambridge: MIT Press. In press."},{"key":"5144388_CR59","unstructured":"Rohanimanesh, K., and Mahadevan, S. Structured approximation of stochastic temporally extended actions. In preparation."},{"key":"5144388_CR60","unstructured":"Rohanimanesh, K., and Mahadevan, S. 2001. Decision-theoretic planning with concurrent temporally extended actions. InProceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence."},{"key":"5144388_CR61","volume-title":"Introduction to Stochastic Dynamic Programming","author":"S. Ross","year":"1983","unstructured":"Ross. S. 1983. Introduction to Stochastic Dynamic Programming. New York: Academic Press."},{"key":"5144388_CR62","unstructured":"Rummery, G. A., and Niranjan, M. 1994. On-line q-learrnng using connectionist systems. Technical Report CUED\/F-INFENG\/'FR 166, Cambridge University Engineering Department."},{"key":"5144388_CR63","first-page":"211","volume":"3","author":"A. L. Samuel","year":"1963","unstructured":"Samuel. A. L. 1963. Some studies in machine learning using the game of checkers. IBM Journal on Research and Developntent 3: 211-229, 1959. Reprinted in E. A. Feigenbaurn and J. Feldman (eds.), Computers and Thought. New York: McGraw-Hill, pp. pp71-105.","journal-title":"IBM Journal on Research and Developntent"},{"key":"5144388_CR64","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1147\/rd.116.0601","volume":"11","author":"A. L. Samuel","year":"1967","unstructured":"Samuel. A. L. 1967. Some studies in machine learning using the game of checkers. Il-Recent progress. IBM Journal on Research and Development 11: 601-617.","journal-title":"IBM Journal on Research and Development"},{"key":"5144388_CR65","doi-asserted-by":"crossref","unstructured":"Schwartz, A. 1993. A reinforcement learning method for maximizing undiscounted rewards. In Proceedings of the Tenth International Conference on Machine Learning. Morgan Kaufmann, pp. 298-305.","DOI":"10.1016\/B978-1-55860-307-3.50045-9"},{"key":"5144388_CR66","first-page":"920","volume":"2","author":"H. Shatkay","year":"1997","unstructured":"Shatkay, H., and Kaelbling. L. P. 1997. Learning topological maps with weak local odometric information. In IJC4I (2). 920-929.","journal-title":"IJC4I"},{"key":"5144388_CR67","first-page":"974","volume-title":"Advances in Neural Information Processing Systems: Proceedings of the 1996 conference","author":"S. Singh","year":"1997","unstructured":"Singh. S., and Bertsekas, D. 1997. Reinforcement learning for dynamic channel allocation in cellular telephone systems. In Advances in Neural Information Processing Systems: Proceedings of the 1996 conference. Cambridge, MA: MIT Press, pp. 974-980."},{"key":"5144388_CR68","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S. Singh","year":"2000","unstructured":"Singh, S., Jaakkola, T., Littman, M. L., and Szepesv\u00e1ri. C. 2000. Convergence results for single-step on-policy reinforcement-learning algorithms. Machine Learning 38: 287-308.","journal-title":"Machine Learning"},{"key":"5144388_CR69","first-page":"202","volume-title":"Proceedings of the Tenth Notional Conference on Artificial Intelligence","author":"S. P. Singh","year":"1992","unstructured":"Singh, S. P. 1992. Reinforcement learning with a hierarchy of abstract models. In Proceedings of the Tenth Notional Conference on Artificial Intelligence. Menlo Park, CA: AAAI Press\/MIT Press, pp. 202-207."},{"key":"5144388_CR70","first-page":"406","volume-title":"In Proceedings of the Ninth International Machine Learning Conference","author":"S. P. Singh","year":"1992","unstructured":"Singh, S. P. 1992. Scaling reinforcement learning algorithms by learning variable temporal resolution models. In Proceedings of the Ninth International Machine Learning Conference. San Mateo, CA: Morgan Kaufmann. pp. 406-415."},{"key":"5144388_CR71","first-page":"537","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning","author":"P. Stone","year":"2001","unstructured":"Stone, P., and Sutton, R. S. 2001. Scaling reinforcement learning toward RoboCup soccer. In C. Brodley and A. Danyluk (eds.), Proceedings of the Eighteenth International Conference on Machine Learning. San Francisco, CA: Morgan Kaufmann, pp. 537-544."},{"key":"5144388_CR72","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1023\/A:1007510522680","volume":"33","author":"T. Sugawara","year":"1998","unstructured":"Sugawara, T., and Lesser, V. 1998. Learning to improve coordinated actions in cooperative distributed problem-solving environments. Machine Learning 33: 129-154.","journal-title":"Machine Learning"},{"key":"5144388_CR73","first-page":"1038","volume-title":"Advances in Neural Information Processing Svstenis: Proceedings of the 1995 Conference","author":"R. S. Sutton","year":"1996","unstructured":"Sutton, R. S. 1996. Generalization in reinforcement leaming: Successful examples using sparse coarse coding. In D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo (eds.). Advances in Neural Information Processing Svstenis: Proceedings of the 1995 Conference. Cambridge. MA: MIT Press. pp. 1038-1044."},{"key":"5144388_CR74","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1037\/0033-295X.88.2.135","volume":"88","author":"R. S. Sutton","year":"1981","unstructured":"Sutton, R. S., and Barto, A. G. 1981. Toward a modem theory of adaptive networks: Expectation and prediction. Psychological Review 88: 135-170.","journal-title":"Psychological Review"},{"key":"5144388_CR75","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. Cambridge, MA: MIT Press."},{"key":"5144388_CR76","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. S. Sutton","year":"1999","unstructured":"Sutton, R. S., Precup, D., and Singh, S. 1999. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence 112: 181-211.","journal-title":"Artificial Intelligence"},{"key":"5144388_CR77","first-page":"330","volume-title":"Proceedings of the Tenth International Conference on Mac\/tine Learning","author":"M. Tan","year":"1993","unstructured":"Tan, M. 1993. Multi-agent reinforcement leaming: Independent vs. cooperative agents. In Proceedings of the Tenth International Conference on Mac\/tine Learning. San Francisco, CA: Morgan Kaufmann, pp. 330-337."},{"key":"5144388_CR78","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1023\/A:1022624705476","volume":"8","author":"G. J. Tesauro","year":"1992","unstructured":"Tesauro, G. J. 1992. Practical issues in temporal difference leaming. Machine Learning 8: 257-277.","journal-title":"Machine Learning"},{"issue":"2","key":"5144388_CR79","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G. J. Tesauro","year":"1994","unstructured":"Tesauro, G. J. 1994. TD-gammon, a self-teaching backgammon program, achieves master-level play. Neural Coniputation 6(2): 215-219.","journal-title":"Neural Coniputation"},{"key":"5144388_CR80","unstructured":"Theocharous, G. 2002. Hierarchical Learning and Planning in Partially Observable Markov Derision Processes. Ph.D. Thesis, Michigan State University."},{"key":"5144388_CR81","unstructured":"Theocharous, G., and Mahadevan. S. 2002. Approximate planning with hierarchical partially observable markov decision processs for robot navigation. In Proceedings of the IEEE International Conference on Robotics and Autontation (ICRA)."},{"key":"5144388_CR82","unstructured":"Theocharous, G., Rohanimanesh. K., and Mahadevan, S. 2001. Learning hierarchical partially observable markov decision processs for robot navigation. In Proceedings of the IEEE International Conference o,i Robotics and Automation (ICRA)."},{"key":"5144388_CR83","first-page":"385","volume-title":"Advances tn Neural Information Processing Systems: Proceedings of the 1994 Conference","author":"S. B. Thrun","year":"1995","unstructured":"Thrun, S. B., and Schwartz, A. 1995. Finding structure in reinforcement learning. In G. Tesauro, D. S. Touretzky, and T. Leen (eds.), Advances tn Neural Information Processing Systems: Proceedings of the 1994 Conference. Cambridge, MA: MIT Press, PP. 385-392."},{"key":"5144388_CR84","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J. N. Tsitsikhs","year":"1997","unstructured":"Tsitsikhs, J. N., and Van Roy, B. 1997. An analysis of temporal-difference learning with function approximation. IEEE Transactions on Automatic Control 42: 674-690.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"5144388_CR85","volume-title":"Learning front Delayed Rewards","author":"C. J. C. H. Watkins","year":"1989","unstructured":"Watkins, C. J. C. H. 1989. Learning front Delayed Rewards. Ph.D. thesis, Cambridge, England: Cambridge University."},{"key":"5144388_CR86","first-page":"279","volume":"8","author":"C. J. C. H. Watkins","year":"1992","unstructured":"Watkins, C. J. C. H., and Dayan, P. 1992. Q-learning. Machine Learning 8: 279-292.","journal-title":"Machine Learning"},{"key":"5144388_CR87","volume-title":"Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence","author":"G. Weiss","year":"1999","unstructured":"Weiss, G. 1999. Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence. Cambridge, MA: MIT Press."},{"key":"5144388_CR88","first-page":"25","volume":"22","author":"P. J. Werbos","year":"1977","unstructured":"Werbos, P. J. 1977. Advanced forecasting methods for global crisis warning and models of intelligence. General Systems Yearbook 22: 25-38.","journal-title":"General Systems Yearbook"},{"key":"5144388_CR89","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TSMC.1987.289329","volume":"17","author":"P. J. Werbos","year":"1987","unstructured":"Werbos, P. J. 1987. Building and understanding adaptive systems: A statistical\/numerical approach to factory automation and brain research. IEEE Transactions on Systems, Man, and Cybernetics 17: 7-20.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"5144388_CR90","first-page":"493","volume-title":"Handbook of Intelligent Control: Neural, Fuzzy.and Adaptive Approaches","author":"P. J. Werbos","year":"1992","unstructured":"Werbos, P. J. 1992. Approximate dynamic programming for real-time control and neural modeling. In D. A. White and D. A. Sofge (eds.), Handbook of Intelligent Control: Neural, Fuzzy.and Adaptive Approaches. New York: Van Nostrand Reinhold, pp. 493-325."},{"key":"5144388_CR91","first-page":"591","volume":"13","author":"W. A. Woods","year":"1970","unstructured":"Woods, W. A. 1970. Transition network grammars for natural language analysis.Comntunications of the ACM 13: 591-606.","journal-title":"Transition network grammars for natural language analysis. Comntunications of the ACM"}],"container-title":["Discrete Event Dynamic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1025696116075.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1025696116075\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1025696116075.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T03:58:12Z","timestamp":1753761492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1025696116075"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,10]]},"references-count":91,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2003,10]]}},"alternative-id":["5144388"],"URL":"https:\/\/doi.org\/10.1023\/a:1025696116075","relation":{},"ISSN":["0924-6703","1573-7594"],"issn-type":[{"value":"0924-6703","type":"print"},{"value":"1573-7594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2003,10]]}}}