{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:43:12Z","timestamp":1742946192335,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319606170"},{"type":"electronic","value":"9783319606187"}],"license":[{"start":{"date-parts":[[2017,8,19]],"date-time":"2017-08-19T00:00:00Z","timestamp":1503100800000},"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":[[2018]]},"DOI":"10.1007\/978-3-319-60618-7_33","type":"book-chapter","created":{"date-parts":[[2017,8,18]],"date-time":"2017-08-18T12:18:30Z","timestamp":1503058710000},"page":"330-339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Design and Evaluation of Reinforcement Learning Based AI Agent: A Case Study in Gaming"],"prefix":"10.1007","author":[{"given":"P.","family":"Jayashree","sequence":"first","affiliation":[]},{"given":"K.","family":"Ramakrishnan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,8,19]]},"reference":[{"key":"33_CR1","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Soft_computing"},{"key":"33_CR2","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Chopsticks_(hand_game)"},{"key":"33_CR3","unstructured":"http:\/\/www.wikihow.com\/Always-Win-Chopsticks"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Wu, L., Baldi, P.F.: A scalable machine learning approach to go. In: Advances in Neural Information Processing Systems, pp. 1521\u20131528 (2006)","DOI":"10.7551\/mitpress\/7503.003.0195"},{"issue":"1","key":"33_CR5","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1111\/j.1467-8640.1996.tb00253.x","volume":"12","author":"EM Morales","year":"1996","unstructured":"Morales, E.M.: Learning playing strategies in chess. Comput. Intell. 12(1), 65\u201387 (1996)","journal-title":"Comput. Intell."},{"issue":"1","key":"33_CR6","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1111\/j.1467-8640.1996.tb00251.x","volume":"12","author":"R Gasser","year":"1996","unstructured":"Gasser, R.: Solving nine men\u2019s morris. Comput. Intell. 12(1), 24\u201341 (1996)","journal-title":"Comput. Intell."},{"issue":"1","key":"33_CR7","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1111\/j.1467-8640.1996.tb00250.x","volume":"12","author":"LV Alus","year":"1996","unstructured":"Alus, L.V., Huntjens, M.P.H.: Go-moku solved by new search techniques. Comput. Intell. 12(1), 7\u201323 (1996)","journal-title":"Comput. Intell."},{"issue":"1","key":"33_CR8","first-page":"91","volume":"66","author":"LV Allis","year":"1994","unstructured":"Allis, L.V., Vander, M., Herik, H.J.: Proof number search. AI 66(1), 91\u2013124 (1994)","journal-title":"AI"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Krawiec, K., Szubert, M.G.: Learning n-tuple networks for Othello by co-evolutionary gradient search. In: Proceedings of GECCO, Dublin, pp. 355\u2013362 (2011)","DOI":"10.1145\/2001576.2001626"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Thill, M., Koch, P., Konen, W.: Reinforcement learning with N-tuples on the game connect-4. In: Parallel Problem Solving from Nature, pp. 184\u2013194 (2012)","DOI":"10.1007\/978-3-642-32937-1_19"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Thill, M., Bagheri, S., Koch, P., Konen, W.: Temporal difference learning with eligibility traces for the game connect four. In: Proceedings of IEEE Conference on Computational Intelligence and Games, pp. 1\u20138 (2014)","DOI":"10.1109\/CIG.2014.6932870"},{"issue":"22","key":"33_CR12","first-page":"44","volume":"51","author":"H Bhasin","year":"2012","unstructured":"Bhasin, H., Singla, N.: Genetic based algorithm for N-puzzle problem. Int. J. Comput. Appl. 51(22), 44\u201350 (2012)","journal-title":"Int. J. Comput. Appl."},{"key":"33_CR13","unstructured":"Castillo, L.P., Wrobel, S.: Learning minesweeper with multirelational learning. In: Proceedings of International Joint Conference on Artificial intelligence, Mexico 2003, pp. 533\u2013540 (2003)"},{"key":"33_CR14","volume-title":"Introduction to reinforcement learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to reinforcement learning. MIT Press, Cambridge (1998)"},{"issue":"3","key":"33_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":"33_CR16","unstructured":"Sahu, A.K., Palita, P., Mohanty, A.: TIC-TAC-TOE game between computers: a computational intelligence approach. In: Proceedings of International conference on Frontiers in Intelligent Computing: Theory and Applications. ITER, S.O., Odissa, India (2012)"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Gatti, C.J., Embrechts, M.J., Linton, J.D: Reinforcement learning and the effects of parameter settings in the game of Chung Toi. In: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Anchorage, USA, pp. 3530\u20133535 (2011)","DOI":"10.1109\/ICSMC.2011.6084216"},{"issue":"2","key":"33_CR18","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1287\/ijoc.1080.0305","volume":"21","author":"A Gosavi","year":"2009","unstructured":"Gosavi, A.: Reinforcement learning: a tutorial survey and recent advances. INFORMS J. Comput. 21(2), 178\u2013192 (2009)","journal-title":"INFORMS J. Comput."},{"key":"33_CR19","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"33_CR20","unstructured":"Ghory, I.: Reinforcement learning in board games. Univ. of Bristol, Technical report (2004)"},{"issue":"1","key":"33_CR21","doi-asserted-by":"crossref","first-page":"13","DOI":"10.3233\/ICG-2008-31103","volume":"31","author":"G Kendall","year":"2008","unstructured":"Kendall, G., Parkes, A.J., Spoerer, K.: A survey of NP-complete puzzles. ICGA J. 31(1), 13\u201334 (2008)","journal-title":"ICGA J."}],"container-title":["Advances in Intelligent Systems and Computing","Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2016)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-60618-7_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T04:08:57Z","timestamp":1692936537000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-60618-7_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,19]]},"ISBN":["9783319606170","9783319606187"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-60618-7_33","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2017,8,19]]},"assertion":[{"value":"19 August 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SoCPaR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Soft Computing and Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vellore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 December 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socpar2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}