{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-play-othello-with-deep-neural","title":"Learning to Play Othello with Deep Neural Networks","arxiv_id":"1711.06583","date":"2017-11-17","proceeding":null,"authors":["Paweł Liskowski","Wojciech Jaśkowski","Krzysztof Krawiec"],"abstract":"Achieving superhuman playing level by AlphaGo corroborated the capabilities\nof convolutional neural architectures (CNNs) for capturing complex spatial\npatterns. This result was to a great extent due to several analogies between Go\nboard states and 2D images CNNs have been designed for, in particular\ntranslational invariance and a relatively large board. In this paper, we verify\nwhether CNN-based move predictors prove effective for Othello, a game with\nsignificantly different characteristics, including a much smaller board size\nand complete lack of translational invariance. We compare several CNN\narchitectures and board encodings, augment them with state-of-the-art\nextensions, train on an extensive database of experts' moves, and examine them\nwith respect to move prediction accuracy and playing strength. The empirical\nevaluation confirms high capabilities of neural move predictors and suggests a\nstrong correlation between prediction accuracy and playing strength. The best\nCNNs not only surpass all other 1-ply Othello players proposed to date but\ndefeat (2-ply) Edax, the best open-source Othello player.","url_abs":"http://arxiv.org/abs/1711.06583v1","url_pdf":"http://arxiv.org/pdf/1711.06583v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-to-play-othello-with-deep-neural","repo_url":"https://github.com/wjaskowski/dnnothello","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.06583","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}