[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117030-en":3,"doc-seo-117030-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},117030,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Evolutionary Machine Learning and Games - Chapter Overview - Survey","Evolutionary machine learning (EML) is explored as a versatile approach for games, covering how evolution and machine learning can reinforce each other toward practical research goals. The chapter organizes EM L in-game applications by whether evolution augments machine learning, or machine learning augments evolution, while also noting separate uses of each technique. It surveys content generation, player modeling, and game-playing systems, emphasizing algorithmic creativity and open-endedness.","Springer Nature 2021 LATEX template  \narXiv :2311 . 16172v1 [ cs .NE] 20 Nov 2023  \nEvolutionary Machine Learning and Games  \nJulian Togelius 1,2 , Ahmed Khalifa3 , Sam Earle 1 , Michael Cerny Green 1 and Lisa Soros4  \n1* Computer Science and Engineering, New York University, 370 Jay Street, Brooklyn, 07960, New York, United States of America.  \n[2](2 modl.ai)[ modl.ai](2 modl.ai), Nørrebrogade 184, Copenhagen, 2200, Denmark.  \n3 Institute of Digital Games, University of Malta, 20 Triq L-Esperanto, Msida, MSD2080, Malta.  \n4 Computer Science, Barnard College, 3009 Broadway, New York, New York, 10027, United States of America.  \nAbstract  \nEvolutionary machine learning (EML) has been applied to games in multiple ways, and for multiple different purposes. Importantly, AI research in games is not only about playing games; it is also about generating game content, modeling players, and many other applications. Many of these applications pose interesting problems for EML. We will structure this chapter on EML for games based on whether evolution is used to augment machine learning (ML) or ML is used to augment evolution. For completeness, we also briefly discuss the usage of ML and evolution separately in games.  \nKeywords: Games, Procedural Content Generation, Automated Game  \nPlaying, Player Modeling, NeuroEvolution  \n1 Introduction  \nGames of all sorts (including card games, board games, and video games) provide a rich domain for exploring computational intelligence. In many ways, games reflect the parts of the real world that we as humans find interesting, isolating key facets of our experience and encapsulating them within a tractable and interactive medium.  \nSpringer Nature 2021 LATEX template  \n2 EML and Games  \nBeyond mere entertainment, games provide a unique domain for exploring and evaluating AI. Historically, the intersection of AI and games has focused on agents that play specific games well. In this way, games complement the litany of task environments for AI such as embodied agent control. However, games offer additional challenges beyond reward maximization such as effecting spirited play or emulating the style of particular humans.  \nIn addition to playing games, there are challenges including generating content (such as levels, quests, textures, and characters), modeling players, matching players, and adapting interfaces. Content generation in particular requires deeply creative algorithms capable of understanding the essence of a domain and conjuring up new artifacts. In this way, games also provide an opportunity for exploring concepts such as algorithmic innovation and openendedness.  \nIn this chapter, we survey the application of EML to games. We take an inclusive view of EML, focusing on cases where a ML model is evolved, but including examples of all kinds of interaction between evolution and ML. We also give brief overviews of the use of non-evolutionary ML and non-ML evolution in games, but given the breadth of the topic, those sections are mere sketches.  \nEML can, in one form or another, be applied to almost any AI challenge in games. However, this family of methods has seen much more application in some areas rather than others. Reflecting on this, a relatively large number of examples in this chapter will be from game content generation. But there will also be plenty of examples of game-playing evolutionary ML.  \n2 Machine Learning in Games  \nSome of the earliest advancements in ML are due to research on game-playing. In particular, Samuel’s Checkers player from 1959 [81] was the first example of what we now call reinforcement learning. While programs for Chess [12], Checkers [82], and Go initially built (and usually still build) on some form of tree search, machine-learned board value functions were introduced at an early stage and became crucial to any advanced efforts to play classical board games. These value functions could be learned through supervised learning, reinforcement learning, or some c","cbCaibANqG10ZdOB","https://ap.wps.com/l/cbCaibANqG10ZdOB","pdf",671738,1,27,"English","en",105,"# Introduction\n# EML and Games\n## Machine Learning in Games","[{\"question\":\"Evolutionary machine learning在游戏中的主要应用方向有哪些？\",\"answer\":\"主要包括让进化用于增强机器学习，以及让机器学习用于增强进化；同时也会分别简要讨论进化与机器学习在游戏中的独立用法。\"},{\"question\":\"为什么游戏是研究AI的独特领域？\",\"answer\":\"游戏不仅用于娱乐，还能提供可评估的任务环境。它们在超越单纯最大化奖励方面带来额外挑战，例如实现有风格的玩法或模拟特定人类风格。\"},{\"question\":\"在游戏中，机器学习如何用于内容生成和玩家相关任务？\",\"answer\":\"机器学习可用于生成关卡、任务、纹理与角色等内容，常见形式包括自监督学习方法；同时也用于玩家建模、作弊检测和匹配等任务。\"}]",1785673197,68,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"evolutionary-machine-learning-and-games-chapter-overview-survey","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/evolutionary-machine-learning-and-games-chapter-overview-survey/117030/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Evolutionary machine learning在游戏中的主要应用方向有哪些？","Question",{"text":74,"@type":75},"主要包括让进化用于增强机器学习，以及让机器学习用于增强进化；同时也会分别简要讨论进化与机器学习在游戏中的独立用法。","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"为什么游戏是研究AI的独特领域？",{"text":79,"@type":75},"游戏不仅用于娱乐，还能提供可评估的任务环境。它们在超越单纯最大化奖励方面带来额外挑战，例如实现有风格的玩法或模拟特定人类风格。",{"name":81,"@type":72,"acceptedAnswer":82},"在游戏中，机器学习如何用于内容生成和玩家相关任务？",{"text":83,"@type":75},"机器学习可用于生成关卡、任务、纹理与角色等内容，常见形式包括自监督学习方法；同时也用于玩家建模、作弊检测和匹配等任务。","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]