{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:19:49Z","timestamp":1742912389810,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030820138"},{"type":"electronic","value":"9783030820145"}],"license":[{"start":{"date-parts":[[2021,7,23]],"date-time":"2021-07-23T00:00:00Z","timestamp":1626998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,23]],"date-time":"2021-07-23T00:00:00Z","timestamp":1626998400000},"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\/978-3-030-82014-5_44","type":"book-chapter","created":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T09:05:09Z","timestamp":1626944709000},"page":"634-644","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Markov-Chain-Based Agents for k-Armed Bandit Problem"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5231-6136","authenticated-orcid":false,"given":"Vladyslav","family":"Sarnatskyi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-5261","authenticated-orcid":false,"given":"Igor","family":"Baklan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,23]]},"reference":[{"key":"44_CR1","unstructured":"Babaeizadeh, M., Frosio, I., Tyree, S., Clemons, J., Kautz, J.: Reinforcement learning through asynchronous advantage actor-critic on a GPU (2017)"},{"key":"44_CR2","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/tsmc.1983.6313077","volume":"5","author":"AG Barto","year":"1983","unstructured":"Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 5, 834\u2013846 (1983). https:\/\/doi.org\/10.1109\/tsmc.1983.6313077","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"44_CR3","unstructured":"Clemente, A.V., Castej\u00f3n, H.N., Chandra, A.: Efficient parallel methods for deep reinforcement learning (2017)"},{"key":"44_CR4","unstructured":"Kauten, C.: Super Mario Bros for OpenAI Gym. GitHub (2018). https:\/\/github.com\/Kautenja\/gym-super-mario-bros"},{"key":"44_CR5","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning (2013)"},{"key":"44_CR6","unstructured":"Nair, A., et al.: Massively parallel methods for deep reinforcement learning (2015)"},{"key":"44_CR7","unstructured":"Parisotto, E., Ba, J.L., Salakhutdinov, R.: Actor-mimic: Deep multitask and transfer reinforcement learning (2016)"},{"key":"44_CR8","unstructured":"Rusu, A.A., et al.: Policy distillation (2016)"},{"key":"44_CR9","unstructured":"Schmitt, S., et al.: Kickstarting deep reinforcement learning (2018)"},{"issue":"7587","key":"44_CR10","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"44_CR11","unstructured":"Silver, D., et al.: Mastering chess and shogi by self-play with a general reinforcement learning algorithm (2017)"},{"key":"44_CR12","unstructured":"Staff, N.: NES games (2010). https:\/\/web.archive.org\/web\/20101221005931\/. http:\/\/www.nintendo.com\/consumer\/gameslist\/manuals\/nes_games.pdf"},{"key":"44_CR13","unstructured":"Stooke, A., Abbeel, P.: Accelerated methods for deep reinforcement learning (2019)"},{"key":"44_CR14","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, pp. 25\u201327. MIT Press, Cambridge (2018)"},{"key":"44_CR15","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, pp. 37\u201340. MIT Press, Cambridge (2018)"},{"key":"44_CR16","unstructured":"Wang, G.: A multi-armed bandit MCMC, with applications in sampling from doubly intractable posterior (2019)"},{"key":"44_CR17","unstructured":"Zhou, X., Xiong, Y., Chen, N., Gao, X.: Regime switching bandits (2021)"}],"container-title":["Lecture Notes on Data Engineering and Communications Technologies","Lecture Notes in Computational Intelligence and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-82014-5_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T09:15:03Z","timestamp":1626945303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-82014-5_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,23]]},"ISBN":["9783030820138","9783030820145"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-82014-5_44","relation":{},"ISSN":["2367-4512","2367-4520"],"issn-type":[{"type":"print","value":"2367-4512"},{"type":"electronic","value":"2367-4520"}],"subject":[],"published":{"date-parts":[[2021,7,23]]},"assertion":[{"value":"23 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISDMCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Scientific Conference \u201cIntellectual Systems of Decision Making and Problem of Computational Intelligence\u201d","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zalizniy Port","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ukraine","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 May 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isdmci2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isdmci.ks.ua\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}