{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T03:43:03Z","timestamp":1794541383613,"version":"4.9.1"},"publisher-location":"Boston, MA","reference-count":19,"publisher":"Springer US","isbn-type":[{"value":"9781489976857","type":"print"},{"value":"9781489976871","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-1-4899-7687-1_17","type":"book-chapter","created":{"date-parts":[[2017,4,13]],"date-time":"2017-04-13T08:32:22Z","timestamp":1492072342000},"page":"87-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Average-Reward Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Prasad","family":"Tadepalli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,4,14]]},"reference":[{"issue":"1","key":"17_CR1369","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1137\/S0363012998346621","volume":"41","author":"J Abounadi","year":"2002","unstructured":"Abounadi J, Bertsekas DP, Borkar V (2002) Stochastic approximation for non-expansive maps: application to Q-learning algorithms. SIAM J Control Optim 41(1):1\u201322","journal-title":"SIAM J Control Optim"},{"issue":"1","key":"17_CR1370","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/0004-3702(94)00011-O","volume":"72","author":"AG Barto","year":"1995","unstructured":"Barto AG, Bradtke SJ, Singh SP (1995) Learning to act using real-time dynamic programming. Artif Intell 72(1):81\u2013138","journal-title":"Artif Intell"},{"key":"17_CR1371","volume-title":"Dynamic programming and optimal control","author":"DP Bertsekas","year":"1995","unstructured":"Bertsekas DP (1995) Dynamic programming and optimal control. Athena Scientific, Belmont"},{"key":"17_CR1372","first-page":"213","volume":"2","author":"RI Brafman","year":"2002","unstructured":"Brafman RI, Tennenholtz M (2002) R-MAX \u2013 a general polynomial time algorithm for near-optimal reinforcement learning. J Mach Learn Res 2:213\u2013231","journal-title":"J Mach Learn Res"},{"issue":"2\/3","key":"17_CR1373","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1007518724497","volume":"33","author":"RH Crites","year":"1998","unstructured":"Crites RH, Barto AG (1998) Elevator group control using multiple reinforcement agents. Mach Learn 33(2\/3):235\u2013262","journal-title":"Mach Learn"},{"issue":"2","key":"17_CR1374","first-page":"197","volume":"13","author":"M Ghavamzadeh","year":"2006","unstructured":"Ghavamzadeh M, Mahadevan S (2006) Hierarchical average reward reinforcement learning. J Mach Learn Res 13(2):197\u2013229","journal-title":"J Mach Learn Res"},{"issue":"2\/3","key":"17_CR1375","doi-asserted-by":"publisher","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. Mach Learn 49(2\/3):209\u2013232","journal-title":"Mach Learn"},{"key":"17_CR1376","doi-asserted-by":"crossref","unstructured":"Mahadevan S (1996) Average reward reinforcement learning: foundations, algorithms, and empirical results. Mach Learn 22(1\/2\/3):159\u2013195","DOI":"10.1007\/BF00114727"},{"issue":"2","key":"17_CR1377","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1109\/49.824797","volume":"18","author":"P Marbach","year":"2000","unstructured":"Marbach P, Mihatsch O, Tsitsiklis JN (2000) Call admission control and routing in integrated service networks using neuro-dynamic programming. IEEE J Sel Areas Commun 18(2): 197\u2013208","journal-title":"IEEE J Sel Areas Commun"},{"key":"17_CR1378","first-page":"725","volume-title":"European conference on machine learning","author":"S Proper","year":"2006","unstructured":"Proper S, Tadepalli P (2006) Scaling model-based average-reward reinforcement learning for product delivery. In: European conference on machine learning, Berlin. Springer, pp\u00a0725\u2013742"},{"key":"17_CR1379","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: discrete dynamic stochastic programming","author":"ML Puterman","year":"1994","unstructured":"Puterman ML (1994) Markov decision processes: discrete dynamic stochastic programming. Wiley, New York"},{"key":"17_CR1380","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, Amherst. Morgan Kaufmann, San Mateo, pp\u00a0298\u2013305"},{"key":"17_CR1381","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, Sydney. Morgan Kaufmann, pp\u00a0562\u2013569"},{"key":"17_CR1382","volume-title":"Reinforcement learning: an introduction","author":"R Sutton","year":"1998","unstructured":"Sutton R, Barto A (1998) Reinforcement learning: an introduction. MIT, Cambridge"},{"key":"17_CR1383","doi-asserted-by":"publisher","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. Artif Intell 100:177\u2013224","journal-title":"Artif Intell"},{"issue":"3\u20134","key":"17_CR1384","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1023\/A:1022624705476","volume":"8","author":"G Tesauro","year":"1992","unstructured":"Tesauro G (1992) Practical issues in temporal difference learning. Mach Learn 8(3\u20134):257\u2013277","journal-title":"Mach Learn"},{"issue":"11","key":"17_CR1385","doi-asserted-by":"publisher","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":"17_CR1386","doi-asserted-by":"publisher","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. Mach Learn 49(2\/3):179\u2013191","journal-title":"Mach Learn"},{"key":"17_CR1387","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, Bled, pp\u00a0464\u2013473"}],"container-title":["Encyclopedia of Machine Learning and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4899-7687-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:57:39Z","timestamp":1791817059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4899-7687-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9781489976857","9781489976871"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-1-4899-7687-1_17","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-1-4899-7687-1","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"14 April 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}