{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T07:52:49Z","timestamp":1794383569063,"version":"4.9.0"},"publisher-location":"Boston, MA","reference-count":19,"publisher":"Springer US","isbn-type":[{"value":"9780387307688","type":"print"},{"value":"9780387301648","type":"electronic"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-0-387-30164-8_49","type":"book-chapter","created":{"date-parts":[[2010,12,29]],"date-time":"2010-12-29T12:36:36Z","timestamp":1293626196000},"page":"64-68","source":"Crossref","is-referenced-by-count":1,"title":["Average-Reward Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Prasad","family":"Tadepalli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"issue":"1","key":"49_CR1_49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1137\/S0363012998346621","volume":"41","author":"J Abounadi","year":"2002","unstructured":"Abounadi, J., Bertsekas, D.\u00a0P., & Borkar, V. (2002). Stochastic approximation for non-expansive maps: Application to Q-learning algorithms. SIAM Journal of Control and Optimization, 41(1), 1\u201322.","journal-title":"SIAM Journal of Control and Optimization"},{"issue":"1","key":"49_CR2_49","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/0004-3702(94)00011-O","volume":"72","author":"AG Barto","year":"1995","unstructured":"Barto, A.\u00a0G., Bradtke, S.\u00a0J., & Singh, S.\u00a0P. (1995). Learning to act using real-time dynamic programming. Artificial Intelligence, 72(1), 81\u2013138.","journal-title":"Artificial Intelligence"},{"key":"49_CR3_49","volume-title":"Dynamic programming and optimal control","author":"DP Bertsekas","year":"1995","unstructured":"Bertsekas, D.\u00a0P. (1995). Dynamic programming and optimal control. Belmont, MA: Athena Scientific."},{"key":"49_CR4_49","first-page":"213","volume":"2","author":"RI Brafman","year":"2002","unstructured":"Brafman, R.\u00a0I., & Tennenholtz, M. (2002). R-MAX \u2013 a general polynomial time algorithm for near-optimal reinforcement learning. Journal of Machine Learning Research, 2, 213\u2013231.","journal-title":"Journal of Machine Learning Research"},{"issue":"2\/3","key":"49_CR5_49","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1007518724497","volume":"33","author":"RH Crites","year":"1998","unstructured":"Crites, R.\u00a0H., & Barto, A.\u00a0G. (1998). Elevator group control using multiple reinforcement agents. Machine Learning, 33(2\/3), 235\u2013262.","journal-title":"Machine Learning"},{"issue":"2","key":"49_CR6_49","first-page":"197","volume":"13","author":"M Ghavamzadeh","year":"2006","unstructured":"Ghavamzadeh, M., & Mahadevan, S. (2006). Hierarchical average reward reinforcement learning. Journal of Machine Learning Research, 13(2), 197\u2013229.","journal-title":"Journal of Machine Learning Research"},{"issue":"2\/3","key":"49_CR7_49","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1023\/A:1017984413808","volume":"49","author":"M Kearns","year":"2002","unstructured":"Kearns, M., & Singh S. (2002). Near-optimal reinforcement learning in polynomial time. Machine Learning, 49(2\/3), 209\u2013232.","journal-title":"Machine Learning"},{"key":"49_CR8_49","doi-asserted-by":"crossref","unstructured":"Mahadevan, S. (1996). Average reward reinforcement learning: Foundations, algorithms, and empirical results. Machine Learning, 22(1\/2\/3), 159\u2013195.","DOI":"10.1023\/A:1018064306595"},{"issue":"2","key":"49_CR9_49","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1109\/49.824797","volume":"18","author":"P Marbach","year":"2000","unstructured":"Marbach, P., Mihatsch, O., & Tsitsiklis, J.\u00a0N. (2000). Call admission control and routing in integrated service networks using neuro-dynamic programming. IEEE Journal on Selected Areas in Communications, 18(2), 197\u2013208.","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"49_CR10_49","doi-asserted-by":"crossref","unstructured":"Proper, S., & Tadepalli, P. (2006). Scaling model-based average-reward reinforcement learning for product delivery. In European conference on machine learning (pp. 725\u2013742). Springer.","DOI":"10.1007\/11871842_74"},{"key":"49_CR11_49","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: Discrete dynamic stochastic programming","author":"ML Puterman","year":"1994","unstructured":"Puterman, M.\u00a0L. (1994). Markov decision processes: Discrete dynamic stochastic programming. New York: Wiley."},{"key":"49_CR12_49","first-page":"298","volume-title":"Proceedings of the tenth international conference on machine learning","author":"A Schwartz","year":"1993","unstructured":"Schwartz, A. (1993). A reinforcement learning method for maximizing undiscounted rewards. In Proceedings of the tenth international conference on machine learning (pp. 298\u2013305). San Mateo, CA: Morgan Kaufmann."},{"key":"49_CR13_49","first-page":"562","volume-title":"Proceedings of international machine learning conference","author":"S Seri","year":"2002","unstructured":"Seri, S., & Tadepalli, P. (2002). Model-based hierarchical average-reward reinforcement learning. In Proceedings of international machine learning conference (pp. 562\u2013569). Sydney, Australia: Morgan Kaufmann."},{"key":"49_CR14_49","volume-title":"Reinforcement learning: An introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. (1998). Reinforcement learning: An introduction. Cambridge, MA: MIT Press."},{"key":"49_CR15_49","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/S0004-3702(98)00002-2","volume":"100","author":"P Tadepalli","year":"1998","unstructured":"Tadepalli, P., & Ok, D. (1998). Model-based average-reward reinforcement learning. Artificial Intelligence, 100, 177\u2013224.","journal-title":"Artificial Intelligence"},{"issue":"3\u20134","key":"49_CR16_49","first-page":"257","volume":"8","author":"G Tesauro","year":"1992","unstructured":"Tesauro, G. (1992). Practical issues in temporal difference learning. Machine Learning, 8(3\u20134), 257\u2013277.","journal-title":"Machine Learning"},{"issue":"11","key":"49_CR17_49","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1016\/S0005-1098(99)00099-0","volume":"35","author":"J Tsitsiklis","year":"1999","unstructured":"Tsitsiklis, J., & Van Roy, B. (1999). Average cost temporal-difference learning. Automatica, 35(11), 1799\u20131808.","journal-title":"Automatica"},{"issue":"2\/3","key":"49_CR18_49","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1023\/A:1017980312899","volume":"49","author":"B Van Roy","year":"2002","unstructured":"Van Roy, B., & Tsitsiklis, J. (2002). On average versus discounted temporal-difference learning. Machine Learning, 49(2\/3), 179\u2013191.","journal-title":"Machine Learning"},{"key":"49_CR19_49","unstructured":"Wang, G., & Mahadevan, S. (1999). Hierarchical optimization of policy-coupled semi-Markov decision processes. In Proceedings of the 16th international conference on machine learning (pp.\u00a0464\u2013473). Bled, Slovenia."}],"container-title":["Encyclopedia of Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-0-387-30164-8_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T22:04:25Z","timestamp":1703196265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-0-387-30164-8_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9780387307688","9780387301648"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-0-387-30164-8_49","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-0-387-30164-8","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2011]]}}}