{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:46:40Z","timestamp":1777693600289,"version":"3.51.4"},"reference-count":11,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICG"],"published-print":{"date-parts":[[2021,1,11]]},"abstract":"<jats:p>Since DeepMind\u2019s AlphaZero, Zero learning quickly became the state-of-the-art method for many board games. It can be improved using a fully convolutional structure (no fully connected layer). Using such an architecture plus global pooling, we can create bots independent of the board size. The training can be made more robust by keeping track of the best checkpoints during the training and by training against them. Using these features, we release Polygames, our framework for Zero learning, with its library of games and its checkpoints. We won against strong humans at the game of Hex in 19 \u00d7 19, including the human player with the best ELO rank on LittleGolem; we incidentally also won against another Zero implementation, which was weaker than humans: in a discussion on LittleGolem, Hex19 was said to be intractable for zero learning. We also won in Havannah with size 8: win against the strongest player, namely Eobllor, with excellent opening moves. We also won several first places at the TAAI 2019 competitions and had positive results against strong bots in various games.<\/jats:p>","DOI":"10.3233\/icg-200157","type":"journal-article","created":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T14:21:27Z","timestamp":1598365287000},"page":"244-256","source":"Crossref","is-referenced-by-count":22,"title":["Polygames: Improved zero learning"],"prefix":"10.1177","volume":"42","author":[{"given":"Tristan","family":"Cazenave","sequence":"first","affiliation":[{"name":"LAMSADE, University Paris-Dauphine, PSL, France"}]},{"given":"Yen-Chi","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University, Taiwan"}]},{"given":"Guan-Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Shi-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Xian-Dong","family":"Chiu","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Julien","family":"Dehos","sequence":"additional","affiliation":[{"name":"University Littoral Cote d\u2019Opale, France"}]},{"given":"Maria","family":"Elsa","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Qucheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Hengyuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Vasil","family":"Khalidov","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Cheng-Ling","family":"Li","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Hsin-I","family":"Lin","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Yu-Jin","family":"Lin","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Xavier","family":"Martinet","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Vegard","family":"Mella","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Jeremy","family":"Rapin","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Baptiste","family":"Roziere","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Gabriel","family":"Synnaeve","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Fabien","family":"Teytaud","sequence":"additional","affiliation":[{"name":"University Littoral Cote d\u2019Opale, France"}]},{"given":"Olivier","family":"Teytaud","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]},{"given":"Shi-Cheng","family":"Ye","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Yi-Jun","family":"Ye","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Shi-Jim","family":"Yen","sequence":"additional","affiliation":[{"name":"AILAB, Dong Hwa University, Taiwan"}]},{"given":"Sergey","family":"Zagoruyko","sequence":"additional","affiliation":[{"name":"Facebook AI Research, France and United States"}]}],"member":"179","reference":[{"issue":"7","key":"10.3233\/ICG-200157_ref1","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1142\/S0129054112400576","article-title":"The frontier of decidability in partially observable recursive games","volume":"23","author":"Auger","year":"2012","journal-title":"International Journal of Foundations of Computer Science"},{"key":"10.3233\/ICG-200157_ref2","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.tcs.2016.06.033","article-title":"On the complexity of connection games","volume":"644","author":"Bonnet","year":"2016","journal-title":"Theor. Comput. Sci."},{"key":"10.3233\/ICG-200157_ref3","unstructured":"Buffet, O., Lee, C.-S., Lin, W. & Teytaud, O. (2012). Optimistic heuristics for MineSweeper. In International Computer Symposium, Hualien, Taiwan. https:\/\/hal.inria.fr\/hal-00750577."},{"key":"10.3233\/ICG-200157_ref4","unstructured":"Coulom, R. (2007). Efficient selectivity and backup operators in Monte-Carlo tree search. In Proceedings of the 5th International Conference on Computers and Games. CG\u201906 (pp.\u00a072\u201383). Berlin, Heidelberg: Springer."},{"key":"10.3233\/ICG-200157_ref8","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"10.3233\/ICG-200157_ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27992-3_2"},{"key":"10.3233\/ICG-200157_ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"10.3233\/ICG-200157_ref14","unstructured":"Pitrat, J. (1968). Realization of a general game-playing program. In Information Processing, Proceedings of IFIP Congress 1968, Edinburgh, UK, 5\u201310 August 1968, Volume 2 \u2013 Hardware, Applications (pp.\u00a01570\u20131574)."},{"key":"10.3233\/ICG-200157_ref15","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In N. Navab, J. Hornegger, W.M. Wells and A.F. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015 (pp.\u00a0234\u2013241). Cham.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"10.3233\/ICG-200157_ref16","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully convolutional networks for semantic segmentation","volume":"39","author":"Shelhamer","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7587","key":"10.3233\/ICG-200157_ref17","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"}],"container-title":["ICGA Journal"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/ICG-200157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:13:13Z","timestamp":1777453993000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/ICG-200157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,11]]},"references-count":11,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/icg-200157","relation":{},"ISSN":["2468-2438","1389-6911"],"issn-type":[{"value":"2468-2438","type":"electronic"},{"value":"1389-6911","type":"print"}],"subject":[],"published":{"date-parts":[[2021,1,11]]}}}