{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:22:14Z","timestamp":1742970134358,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319579689"},{"type":"electronic","value":"9783319579696"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","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\/978-3-319-57969-6_1","type":"book-chapter","created":{"date-parts":[[2017,4,28]],"date-time":"2017-04-28T10:04:26Z","timestamp":1493373866000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["NeuroHex: A Deep Q-learning Hex Agent"],"prefix":"10.1007","author":[{"given":"Kenny","family":"Young","sequence":"first","affiliation":[]},{"given":"Gautham","family":"Vasan","sequence":"additional","affiliation":[]},{"given":"Ryan","family":"Hayward","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,4,29]]},"reference":[{"key":"1_CR1","unstructured":"Anshelevich, V.V.: The game of Hex: an automatic theorem proving approach to game programming. In: AAAI\/IAAI, pp. 189\u2013194 (2000)"},{"key":"1_CR2","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3233\/ICG-2009-32111","volume":"32","author":"B Arneson","year":"2008","unstructured":"Arneson, B., Hayward, R., Henderson, P.: Wolve wins Hex tournament. ICGA J. 32, 49\u201353 (2008)","journal-title":"ICGA J."},{"issue":"4","key":"1_CR3","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/TCIAIG.2010.2067212","volume":"2","author":"B Arneson","year":"2010","unstructured":"Arneson, B., Hayward, R.B., Henderson, P.: Monte Carlo tree search in Hex. IEEE Trans. Comput. Intell. AI Games 2(4), 251\u2013258 (2010)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"1_CR4","unstructured":"Bastien, F., Lamblin, P., Pascanu, R., Bergstra, J., Goodfellow, I.J., Bergeron, A., Bouchard, N., Bengio, Y.: Theano: new features and speed improvements. In: NIPS 2012 Deep Learning and Unsupervised Feature Learning Workshop (2012)"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/978-3-642-31866-5_3","volume-title":"Advances in Computer Games","author":"P Baudi\u0161","year":"2012","unstructured":"Baudi\u0161, P., Gailly, J.: PACHI: state of the art open source go program. In: Herik, H.J., Plaat, A. (eds.) ACG 2011. LNCS, vol. 7168, pp. 24\u201338. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-31866-5_3"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: a CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy) (2010). Oral Presentation","DOI":"10.25080\/Majora-92bf1922-003"},{"issue":"1","key":"1_CR7","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1038\/scientificamerican0757-145","volume":"197","author":"M Gardner","year":"1957","unstructured":"Gardner, M.: Mathematical games. Sci. Am. 197(1), 145\u2013150 (1957)","journal-title":"Sci. Am."},{"issue":"3","key":"1_CR8","doi-asserted-by":"publisher","first-page":"180","DOI":"10.3233\/ICG-2013-36318","volume":"36","author":"RB Hayward","year":"2013","unstructured":"Hayward, R.B.: MoHex wins Hex tournament. ICGA J. 36(3), 180\u2013183 (2013)","journal-title":"ICGA J."},{"key":"1_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/978-3-319-09165-5_6","volume-title":"Computers and Games","author":"S-C Huang","year":"2014","unstructured":"Huang, S.-C., Arneson, B., Hayward, R.B., M\u00fcller, M., Pawlewicz, J.: MoHex 2.0: a pattern-based MCTS Hex player. In: Herik, H.J., Iida, H., Plaat, A. (eds.) CG 2013. LNCS, vol. 8427, pp. 60\u201371. Springer, Cham (2014). doi: 10.1007\/978-3-319-09165-5_6"},{"issue":"7540","key":"1_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)","journal-title":"Nature"},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/BF00288964","volume":"15","author":"S Reisch","year":"1981","unstructured":"Reisch, S.: Hex ist PSPACE-vollst\u00e4ndig. Acta Informatica 15, 167\u2013191 (1981)","journal-title":"Acta Informatica"},{"key":"1_CR12","first-page":"1234","volume":"41","author":"CE Shannon","year":"1953","unstructured":"Shannon, C.E.: Computers and automata. Proc. Inst. Radio Eng. 41, 1234\u20131241 (1953)","journal-title":"Proc. Inst. Radio Eng."},{"issue":"7587","key":"1_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., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"1_CR14","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"3","key":"1_CR15","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(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"key":"1_CR16","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5\u2013RmsProp: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw. Mach. Learn. (2012)"}],"container-title":["Communications in Computer and Information Science","Computer Games"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-57969-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T13:09:31Z","timestamp":1601989771000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-57969-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319579689","9783319579696"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-57969-6_1","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"29 April 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}