{"id":"https://openalex.org/W4221017035","doi":"https://doi.org/10.1145/3489525.3511685","title":"The Cost of Reinforcement Learning for Game Engines","display_name":"The Cost of Reinforcement Learning for Game Engines","publication_year":2022,"publication_date":"2022-03-25","ids":{"openalex":"https://openalex.org/W4221017035","doi":"https://doi.org/10.1145/3489525.3511685"},"language":"en","primary_location":{"id":"doi:10.1145/3489525.3511685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489525.3511685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SPEC on International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009497746","display_name":"Danilo de Goede","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Danilo de Goede","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001068033","display_name":"Duncan Kampert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090210","display_name":"SURF","ror":"https://ror.org/009vhk114","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210090210"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Duncan Kampert","raw_affiliation_strings":["SURF, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"SURF, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210090210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109847155","display_name":"Ana Lucia V\u0103rb\u0103nescu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ana Lucia Varbanescu","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009497746"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.1378,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51390749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11197","display_name":"Digital Games and Media","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8231738209724426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355826497077942},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6237896680831909},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5629345178604126},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47828301787376404},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47352123260498047},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4687854051589966},{"id":"https://openalex.org/keywords/game-design","display_name":"Game design","score":0.4531335234642029},{"id":"https://openalex.org/keywords/game-engine","display_name":"Game engine","score":0.4522344768047333},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.42889881134033203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38242387771606445},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32159170508384705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8231738209724426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355826497077942},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6237896680831909},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5629345178604126},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47828301787376404},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47352123260498047},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4687854051589966},{"id":"https://openalex.org/C503285160","wikidata":"https://www.wikidata.org/wiki/Q858057","display_name":"Game design","level":2,"score":0.4531335234642029},{"id":"https://openalex.org/C2986528223","wikidata":"https://www.wikidata.org/wiki/Q193564","display_name":"Game engine","level":2,"score":0.4522344768047333},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.42889881134033203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38242387771606445},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32159170508384705},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3489525.3511685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489525.3511685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SPEC on International Conference on Performance Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:publications/d02afab4-552b-4a0a-8b83-2beda2091890","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/the-cost-of-reinforcement-learning-for-game-engines-the-azhive-casestudy(d02afab4-552b-4a0a-8b83-2beda2091890).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"de Goede, D, Kampert, D & Varbanescu, A-L 2022, The Cost of Reinforcement Learning for Game Engines: The AZ-Hive Case-study. in ICPE '22 : proceedings of the 2022 ACM/SPEC International Conference on Performance Engineering : April 9-13, 2022, Bejing, China. New York, NY, pp. 145-152, 13th ACM/SPEC International Conference on Performance Engineering, Beijing, China, 9/04/22. https://doi.org/10.1145/3489525.3511685","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1970647289","https://openalex.org/W2033016725","https://openalex.org/W2167198292","https://openalex.org/W2257979135","https://openalex.org/W2766447205","https://openalex.org/W2902907165","https://openalex.org/W2989847975","https://openalex.org/W3037261029","https://openalex.org/W3043273434","https://openalex.org/W3081484978","https://openalex.org/W3109309915","https://openalex.org/W3118210634","https://openalex.org/W3174469560"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W2346475595","https://openalex.org/W2140829396","https://openalex.org/W2116985439","https://openalex.org/W2253573968","https://openalex.org/W2354051889","https://openalex.org/W3094497437","https://openalex.org/W2068567675","https://openalex.org/W2368656633"],"abstract_inverted_index":{"Although":[0],"utilising":[1],"computers":[2],"to":[3,100,135,172],"play":[4,96,101],"board":[5],"games":[6,36],"has":[7],"been":[8],"a":[9,65,93,148,173],"topic":[10],"of":[11,23,45,59,83,89,95,129,160,198,212],"research":[12],"for":[13,80,151,184],"many":[14],"decades,":[15],"the":[16,21,43,55,60,81,87,90,102,113,119,121,124,127,156,180,199],"recent":[17],"rapid":[18],"developments":[19],"in":[20,35,115,163],"field":[22],"reinforcement":[24],"learning":[25],"-":[26,31],"like":[27],"AlphaZero":[28,61],"and":[29,40,57,92,109,126,154,158,182],"variants":[30],"brought":[32],"unprecedented":[33],"progress":[34],"such":[37,186],"as":[38],"chess":[39],"Go.":[41],"However,":[42],"efficiency":[44,58],"this":[46,51,164],"process":[47],"remains":[48],"unknown.":[49],"In":[50,203],"work,":[52],"we":[53,70,146],"analyse":[54],"cost":[56],"approach":[62],"when":[63],"building":[64,74],"new":[66],"game":[67,82,91,103,114,122],"engine.":[68],"Thus,":[69,145],"present":[71],"our":[72],"experience":[73],"AZ-Hive,":[75,153],"an":[76,205],"AlphaZero-based":[77],"playing":[78],"engine":[79],"Hive.":[84],"Using":[85],"only":[86],"rules":[88,125],"quality":[94],"assessment,":[97],"AZ-Hive":[98,107,138],"learns":[99],"from":[104],"scratch.":[105],"Getting":[106],"up":[108],"running":[110],"requires":[111],"encoding":[112],"AlphaZero,":[116],"i.e.,":[117],"capturing":[118],"board,":[120],"state,":[123],"assessment":[128],"play-quality.":[130],"And":[131],"different":[132,137,142,161,169,185],"encodings":[133],"lead":[134,171],"significantly":[136],"engines,":[139],"with":[140],"very":[141],"performance":[143],"results.":[144],"propose":[147],"design":[149],"space":[150,200],"configuring":[152],"demonstrate":[155],"costs":[157],"benefits":[159],"configurations":[162,170],"space.":[165],"We":[166],"find":[167],"that":[168],"less":[174],"or":[175,196],"more":[176],"competitive":[177],"playing-engine,":[178],"but":[179],"training":[181],"evaluation":[183],"engines":[187],"is":[188,201],"prohibitively":[189],"expensive.":[190],"Moreover,":[191],"no":[192],"systematic,":[193],"efficient":[194],"exploration":[195,207],"pruning":[197],"possible.":[202],"turn,":[204],"exhaustive":[206],"can":[208],"easily":[209],"take":[210],"tens":[211],"training-years.":[213]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}