{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:16:16Z","timestamp":1743066976671,"version":"3.40.3"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031086229"},{"type":"electronic","value":"9783031086236"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-08623-6_60","type":"book-chapter","created":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T07:06:24Z","timestamp":1661756784000},"page":"409-414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Routing in\u00a0Reinforcement Learning Markov Chains"],"prefix":"10.1007","author":[{"given":"Maximilian","family":"Moll","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominic","family":"Weller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,30]]},"reference":[{"key":"60_CR1","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"issue":"1","key":"60_CR2","first-page":"125","volume":"11","author":"X Cui","year":"2011","unstructured":"Cui, X., Shi, H.: A*-based pathfinding in modern computer games. Int. J. Comput. Sci. Netw. Secur. 11(1), 125\u2013130 (2011)","journal-title":"Int. J. Comput. Sci. Netw. Secur."},{"key":"60_CR3","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1613\/jair.1373","volume":"21","author":"A Felner","year":"2004","unstructured":"Felner, A., Stern, R., Ben-Yair, A., Kraus, S., Netanyahu, N.: PHA*: finding the shortest path with A* in an unknown physical environment. J. Artif. Intell. Res. 21, 631\u2013670 (2004)","journal-title":"J. Artif. Intell. Res."},{"key":"60_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106244","volume":"204","author":"Y Hu","year":"2020","unstructured":"Hu, Y., Yao, Y., Lee, W.S.: A reinforcement learning approach for optimizing multiple traveling salesman problems over graphs. Knowl. Based Syst. 204, 106244 (2020)","journal-title":"Knowl. Based Syst."},{"key":"60_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400","volume":"134","author":"N Mazyavkina","year":"2021","unstructured":"Mazyavkina, N., Sviridov, S., Ivanov, S., Burnaev, E.: Reinforcement learning for combinatorial optimization: a survey. Comput. Oper. Res. 134, 105400 (2021)","journal-title":"Comput. Oper. Res."},{"key":"60_CR6","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"60_CR7","doi-asserted-by":"crossref","unstructured":"Moll, M.: Towards extending algorithmic strategy planning in system dynamics modeling. In: 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), pp. 1047\u20131051. IEEE (2017)","DOI":"10.1109\/IEEM.2017.8290052"},{"key":"60_CR8","unstructured":"Moore, A.W.: Efficient memory-based learning for robot control (1990)"},{"issue":"6419","key":"60_CR9","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"issue":"7676","key":"60_CR10","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"60_CR11","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"issue":"7782","key":"60_CR12","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"}],"container-title":["Lecture Notes in Operations Research","Operations Research Proceedings 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08623-6_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T07:10:27Z","timestamp":1661757027000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08623-6_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031086229","9783031086236"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08623-6_60","relation":{},"ISSN":["2731-040X","2731-0418"],"issn-type":[{"type":"print","value":"2731-040X"},{"type":"electronic","value":"2731-0418"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"30 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"OR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Operations Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"or2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.or2021.unibe.ch\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}