{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T10:31:26Z","timestamp":1790159486556,"version":"4.1.0"},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540453758","type":"print"},{"value":"9783540460565","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11871842_74","type":"book-chapter","created":{"date-parts":[[2006,9,18]],"date-time":"2006-09-18T08:28:47Z","timestamp":1158568127000},"page":"735-742","source":"Crossref","is-referenced-by-count":12,"title":["Scaling Model-Based Average-Reward Reinforcement Learning for Product Delivery"],"prefix":"10.1007","author":[{"given":"Scott","family":"Proper","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prasad","family":"Tadepalli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"74_CR1","volume-title":"Reinforcement learning: An introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)"},{"key":"74_CR2","volume-title":"Handbook of Learning and Approximate Dynamic Programming","author":"W.B. Powell","year":"2004","unstructured":"Powell, W.B., Van Roy, B.: Approximate Dynamic Programming for High-Dimensional Dynamic Resource Allocation Problems. In: Si, J., Barto, A.G., Powell, W.B., Wunsch, D. (eds.) Handbook of Learning and Approximate Dynamic Programming. Wiley-IEEE Press, Hoboken (2004)"},{"key":"74_CR3","doi-asserted-by":"crossref","unstructured":"Van Roy, B., Bertsekas, D.P., Lee, Y., Tsitsiklis, J.N.: A Neuro-Dynamic Programming Approach to Retailer Inventory Management. In: Proceedings of the IEEE Conference on Decision and Control (1997)","DOI":"10.1109\/CDC.1997.652501"},{"key":"74_CR4","doi-asserted-by":"crossref","unstructured":"Secamondi, N.: Comparing Neuro-Dynamic Programming Algorithms for the Vehicle Routing Problem with Stochastic Demands. Computers and Operations Research 27(11-12) (2000)","DOI":"10.1016\/S0305-0548(99)00146-X"},{"issue":"5","key":"74_CR5","first-page":"768","volume":"49","author":"N. Secamondi","year":"2001","unstructured":"Secamondi, N.: A Rollout Policy for the Vehicle Routing Problem with Stochastic Demands. Operations Research\u00a049(5), 768\u2013802 (2001)","journal-title":"Operations Research"},{"key":"74_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-540-32274-0_17","volume-title":"Adaptive Agents and Multi-Agent Systems II","author":"M. Strens","year":"2005","unstructured":"Strens, M., Windelinckx, N.: Combining planning with reinforcement learning for multi-robot task allocation. In: Kudenko, D., Kazakov, D., Alonso, E. (eds.) AAMAS 2004. LNCS, vol.\u00a03394, pp. 260\u2013274. Springer, Heidelberg (2005)"},{"key":"74_CR7","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Dynamic Stochastic Programming","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Dynamic Stochastic Programming. John Wiley, Chichester (1994)"},{"key":"74_CR8","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.: Model-based Average Reward Reinforcement Learning. Artificial Intelligence\u00a0100, 177\u2013224 (1998)","journal-title":"Artificial Intelligence"},{"key":"74_CR9","unstructured":"Br\u00e4ysy, O., Gendreau, M.: Vehicle Routing Problem with Time Windows, Part II: Metaheuristics. Working Paper, SINTEF Applied Mathematics, Department of Optimisation, Norway (2003)"},{"key":"74_CR10","first-page":"1114","volume-title":"AAMAS","author":"M. Ghavamzadeh","year":"2004","unstructured":"Ghavamzadeh, M., Mahadevan, S.: Learning to communicate and act using hierarchical reinforcement learning. In: AAMAS, pp. 1114\u20131121. IEEE Computer Society, Los Alamitos (2004)"},{"key":"74_CR11","volume-title":"Proceedings of the 19th International Conference on Machine Learning","author":"C. Guestrin","year":"2002","unstructured":"Guestrin, C., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: Proceedings of the 19th International Conference on Machine Learning. Morgan Kaufmann, San Francisco, CA (2002)"},{"key":"74_CR12","first-page":"298","volume-title":"Proceedings of the 10th International Conference on Machine Learning","author":"A. Schwartz","year":"1993","unstructured":"Schwartz, A.: A Reinforcement Learning Method for Maximizing Undiscounted Rewards. In: Proceedings of the 10th International Conference on Machine Learning, Amherst, Massachusetts, pp. 298\u2013305. Morgan Kaufmann, San Francisco (1993)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2006"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11871842_74.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T07:24:18Z","timestamp":1619508258000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11871842_74"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540453758","9783540460565"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/11871842_74","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}