{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:46:40Z","timestamp":1781016400880,"version":"3.54.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tg.2020.2990865","type":"journal-article","created":{"date-parts":[[2020,5,30]],"date-time":"2020-05-30T00:52:49Z","timestamp":1590799969000},"page":"199-212","source":"Crossref","is-referenced-by-count":32,"title":["Winning Is Not Everything: Enhancing Game Development With Intelligent Agents"],"prefix":"10.1109","volume":"12","author":[{"given":"Yunqi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0861-0001","authenticated-orcid":false,"given":"Igor","family":"Borovikov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7456-910X","authenticated-orcid":false,"given":"Fernando","family":"de Mesentier Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1998-5271","authenticated-orcid":false,"given":"Ahmad","family":"Beirami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Rupert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0045-7687","authenticated-orcid":false,"given":"Caedmon","family":"Somers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesse","family":"Harder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Kolen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jervis","family":"Pinto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reza","family":"Pourabolghasem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Pestrak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harold","family":"Chaput","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohsen","family":"Sardari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sundeep","family":"Narravula","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Navid","family":"Aghdaie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0678-1624","authenticated-orcid":false,"given":"Kazi","family":"Zaman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4913"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1075\/ijcl.22.2.03wri"},{"key":"ref71","first-page":"403","article-title":"In search of lexical discriminators of definition style: Comparing dictionaries through $n$-Grams","volume":"29","author":"kami?ski","year":"2016","journal-title":"Int J Lexicography"},{"key":"ref70","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref76","author":"gersho","year":"1991","journal-title":"Vector Quantization and Signal Compression"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-8180-7_7"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14923-3_5"},{"key":"ref75","author":"oppenheim","year":"1975","journal-title":"Digital Signal Processing"},{"key":"ref38","article-title":"Implementing a computer player for Carcassonne","author":"heyden","year":"2009"},{"key":"ref78","author":"hughes","year":"2013","journal-title":"Computer Graphics"},{"key":"ref79","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1147\/rd.33.0210"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63519-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2846639"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2011.2148116"},{"key":"ref37","first-page":"216","article-title":"Monte-Carlo tree search: A new framework for game AI","author":"chaslot","year":"0","journal-title":"Proc Artif Intell Interactive Digit Entertain Int Conf"},{"key":"ref36","first-page":"21","article-title":"Monte-Carlo tree search in Settlers of Catan","author":"szita","year":"2009","journal-title":"Advances in Computer Games"},{"key":"ref35","first-page":"282","article-title":"Bandit based Monte-Carlo planning","author":"kocsis","year":"0","journal-title":"Proc Eur Conf Mach Learn"},{"key":"ref34","first-page":"72","article-title":"Efficient selectivity and backup operators in Monte-Carlo tree search","author":"coulom","year":"0","journal-title":"Proc Int Conf Comput Games"},{"key":"ref60","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32323-2_11"},{"key":"ref61","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume":"70","author":"bellemare","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref63","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1822348.1822376"},{"key":"ref64","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"213","article-title":"Sentient sketchbook: Computer-aided game level authoring","author":"liapis","year":"0","journal-title":"Proc Int Conf Foundations Dig Games"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref29","first-page":"215","article-title":"Ropossum: An authoring tool for designing, optimizing and solving cut the rope levels","author":"shaker","year":"0","journal-title":"Proc Artif Intell Interactive Digit Entertain Int Conf"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1504\/IJISTA.2007.012489"},{"key":"ref68","first-page":"1087","article-title":"One-shot imitation learning","author":"duan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref2","article-title":"Imitation learning via bootstrapped demonstrations in an open-world video game","author":"borovikov","year":"0","journal-title":"workshop on Reinforcement Learning under Partial Observability 32nd Neurips"},{"key":"ref1","first-page":"159","article-title":"Exploring gameplay with AI agents","author":"silva","year":"0","journal-title":"Proc Artif Intell Interactive Digit Entertain Int Conf"},{"key":"ref20","article-title":"Algorithmically balancing a collectible card game","author":"krucher","year":"2015"},{"key":"ref22","first-page":"1","article-title":"Evolving the hearthstone meta","author":"silva","year":"0","journal-title":"Proc IEEE Conf Games"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2012.6256441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848057"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2808198"},{"key":"ref26","first-page":"1","article-title":"Mixed-initiative co-creativity","author":"yannakakis","year":"0","journal-title":"Proc 9th Conf Found Digit Games"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490417"},{"key":"ref50","year":"2016"},{"key":"ref51","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref59","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2015","journal-title":"arXiv 1511 04143"},{"key":"ref58","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref57","first-page":"2329","article-title":"Point-based value iteration for continuous POMDPs","volume":"7","author":"porta","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1659"},{"key":"ref55","first-page":"1332","article-title":"Solving POMDPs with continuous or large discrete observation spaces","author":"hoey","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref54","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv 1703 03864"},{"key":"ref53","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2017","journal-title":"arXiv 1710 02298"},{"key":"ref52","author":"bellemare","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref40","article-title":"An MCTS agent for ticket to ride","author":"huchler","year":"2015"},{"key":"ref12","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2009.5286500"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2213600"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2012.10.001"},{"key":"ref16","article-title":"Heuristics and usability guidelines for the creation and evaluation of fun in video games","author":"federoff","year":"2002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/9781118796443.ch12"},{"key":"ref18","first-page":"1","article-title":"AI-based playtesting of contemporary board games","author":"silva","year":"0","journal-title":"Proc Int Conf Found Digit Games"},{"key":"ref19","first-page":"25","article-title":"Automatic design of balanced board games","author":"hom","year":"0","journal-title":"Proc AAAI Conf Artif Intell Interact Digit Entertainment"},{"key":"ref80","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref4","article-title":"Winning isn’t everything: Training agents to playtest modern games","author":"borovikov","year":"0","journal-title":"Proc AAAI Workshop Reinforcement Learn Games"},{"key":"ref3","article-title":"Training agents to play modern games: Challenges and opportunities","author":"zhao","year":"0","journal-title":"workshop on Reinforcement Learning under Partial Observability 32nd Neurips"},{"key":"ref6","article-title":"Towards interactive training of non-player characters in video games","author":"borovikov","year":"2019","journal-title":"arXiv 1906 00535"},{"key":"ref5","article-title":"From demonstrations and knowledge engineering to a DNN agent in a modern open-world video game","author":"borovikov","year":"0","journal-title":"Proc AAAI Spring Symp Combining Mach Learn Know Eng"},{"key":"ref8","article-title":"Towards a representative metric of behavior style in imitation and reinforcement learning","author":"borovikov","year":"0","journal-title":"Proc 23rd Annu Signal Image Sci Workshop"},{"key":"ref7","article-title":"On multi-agent learning in team sports games","author":"zhao","year":"0","journal-title":"Proc ICML Workshop Imitation Intent Interact"},{"key":"ref49","first-page":"998","article-title":"Playing Atari with six neurons","author":"cuccu","year":"0","journal-title":"Proc 8th Int Conf Auton Agents Multiagent Syst"},{"key":"ref9","article-title":"Interactive Training (code base)","author":"borovikov","year":"2019"},{"key":"ref46","article-title":"Mastering Chess and Shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"arXiv 1712 01815"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref48","year":"2018"},{"key":"ref47","first-page":"3215","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"0","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2835764"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref43","year":"2018"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/9119230\/09104019.pdf?arnumber=9104019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T12:55:57Z","timestamp":1651064157000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9104019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":80,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2020.2990865","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}