{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:48:04Z","timestamp":1743090484340,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030671471"},{"type":"electronic","value":"9783030671488"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-67148-8_14","type":"book-chapter","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T13:14:58Z","timestamp":1612358098000},"page":"192-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Distributional Temporal Difference Learning for Game Playing"],"prefix":"10.1007","author":[{"given":"Frej","family":"Berglind","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Sopasakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,4]]},"reference":[{"key":"14_CR1","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. CoRR abs\/1707.06887 (2017). http:\/\/arxiv.org\/abs\/1707.06887"},{"issue":"6","key":"14_CR2","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1090\/S0002-9904-1954-09848-8","volume":"60","author":"R Bellman","year":"1954","unstructured":"Bellman, R.: The theory of dynamic programming. Bull. Am. Math. Soc. 60(6), 503\u2013516 (1954)","journal-title":"Bull. Am. Math. Soc."},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Berglind, F.: Deep distributional temporal difference learning for game playing. Master\u2019s thesis, Lund University (2020)","DOI":"10.1007\/978-3-030-67148-8_14"},{"key":"14_CR4","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R.B., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., He, K.: Accurate, large minibatch SGD: training imagenet in 1\u00a0h. CoRR abs\/1706.02677 (2017). http:\/\/arxiv.org\/abs\/1706.02677"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR6","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. CoRR abs\/1603.05027 (2016). http:\/\/arxiv.org\/abs\/1603.05027"},{"key":"14_CR7","unstructured":"Irpan, A.: Deep reinforcement learning doesn\u2019t work yet (2018). https:\/\/www.alexirpan.com\/2018\/02\/14\/rl-hard.html"},{"key":"14_CR8","unstructured":"Ailis, L.V., van den Herik, H.J., Huntjens, M.H.: GoMoku solved by new search techniques. AAAI Technical Report FS-93-02 (1993). https:\/\/www.aaai.org\/Papers\/Symposia\/Fall\/1993\/FS-93-02\/FS93-02-001.pdf"},{"key":"14_CR9","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning, NIPS Deep Learning Workshop (2013). arxiv:1312.5602"},{"issue":"7540","key":"14_CR10","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"14_CR11","volume-title":"Artificial Intelligence: A Modern Approach","author":"S Russell","year":"2009","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Prentice Hall Press, Upper Saddle River (2009)","edition":"3"},{"issue":"3","key":"14_CR12","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1147\/rd.33.0210","volume":"3","author":"AL Samuel","year":"1959","unstructured":"Samuel, A.L.: Some studies in machine learning using the game of checkers. IBM J. Res. Dev. 3(3), 210\u2013229 (1959). https:\/\/doi.org\/10.1147\/rd.33.0210","journal-title":"IBM J. Res. Dev."},{"key":"14_CR13","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T.P., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016)","journal-title":"Nature"},{"key":"14_CR14","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., Lillicrap, T., Simonyan, K., Hassabis, D.: Mastering chess and shogi by self-play with a general reinforcement learning algorithm (2017)"},{"key":"14_CR15","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., Hubert, T., Baker, L.R., Lai, M., Bolton, A., Chen, Y., Lillicrap, T.P., Hui, F., Sifre, L., van den Driessche, G., Graepel, T., Hassabis, D.: Mastering the game of go without human knowledge. Nature 550, 354\u2013359 (2017)","journal-title":"Nature"},{"issue":"2","key":"14_CR16","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s10994-012-5280-0","volume":"87","author":"D Silver","year":"2012","unstructured":"Silver, D., Sutton, R.S., M\u00fcller, M.: Temporal-difference search in computer go. Mach. Learn. 87(2), 183\u2013219 (2012). https:\/\/doi.org\/10.1007\/s10994-012-5280-0","journal-title":"Mach. Learn."},{"key":"14_CR17","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3, 9\u201344 (1988)","journal-title":"Mach. Learn."},{"key":"14_CR18","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, Cambridge (2018). http:\/\/incompleteideas.net\/book\/the-book-2nd.html","edition":"2"},{"key":"14_CR19","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38, 58\u201368 (1995)","journal-title":"Commun. ACM"},{"key":"14_CR20","unstructured":"Watkins, C.: Learning from delayed rewards. Ph.D. thesis, Cambridge University (1989)"},{"key":"14_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63519-4","volume-title":"Artificial Intelligence and Games","author":"GN Yannakakis","year":"2018","unstructured":"Yannakakis, G.N., Togelius, J.: Artificial Intelligence and Games. Springer, Cham (2018). http:\/\/gameaibook.org"}],"container-title":["Studies in Computational Intelligence","Intelligent Systems in Industrial Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67148-8_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T16:41:34Z","timestamp":1619282494000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67148-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030671471","9783030671488"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67148-8_14","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"4 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISMIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Methodologies for Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Graz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ismis2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ismis.ist.tugraz.at\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"8","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}