{"id":"https://openalex.org/W4401943686","doi":"https://doi.org/10.1109/cog60054.2024.10645598","title":"Scaling, Control and Generalization in Reinforcement Learning Level Generators","display_name":"Scaling, Control and Generalization in Reinforcement Learning Level Generators","publication_year":2024,"publication_date":"2024-08-05","ids":{"openalex":"https://openalex.org/W4401943686","doi":"https://doi.org/10.1109/cog60054.2024.10645598"},"language":"en","primary_location":{"id":"doi:10.1109/cog60054.2024.10645598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog60054.2024.10645598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088834644","display_name":"Sam Earle","orcid":"https://orcid.org/0000-0003-3783-9486"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Earle","raw_affiliation_strings":["New York University,Game Innovation Lab,NY,Brooklyn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Game Innovation Lab,NY,Brooklyn","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101465889","display_name":"Zehua Jiang","orcid":"https://orcid.org/0000-0003-1807-7826"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zehua Jiang","raw_affiliation_strings":["New York University,Game Innovation Lab,NY,Brooklyn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Game Innovation Lab,NY,Brooklyn","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077267552","display_name":"Julian Togelius","orcid":"https://orcid.org/0000-0003-3128-4598"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Togelius","raw_affiliation_strings":["New York University,Game Innovation Lab,NY,Brooklyn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Game Innovation Lab,NY,Brooklyn","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9966999888420105,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7757486701011658},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7661789655685425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6213703751564026},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6206225156784058},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.557896077632904},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.4515865445137024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44128406047821045},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4118348956108093},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18141454458236694},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17209845781326294},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10713732242584229}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7757486701011658},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7661789655685425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6213703751564026},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6206225156784058},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.557896077632904},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.4515865445137024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44128406047821045},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4118348956108093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18141454458236694},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17209845781326294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10713732242584229},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog60054.2024.10645598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog60054.2024.10645598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2108806781","https://openalex.org/W2152660354","https://openalex.org/W2168115594","https://openalex.org/W2534314849","https://openalex.org/W2546680972","https://openalex.org/W2736601468","https://openalex.org/W2963690854","https://openalex.org/W2964201809","https://openalex.org/W2972248814","https://openalex.org/W3092157356","https://openalex.org/W3093908578","https://openalex.org/W3105926098","https://openalex.org/W3159533820","https://openalex.org/W4205590214","https://openalex.org/W4283731822","https://openalex.org/W4289492459","https://openalex.org/W4305038385","https://openalex.org/W4312853411","https://openalex.org/W4392223126","https://openalex.org/W4401980028","https://openalex.org/W6741002519","https://openalex.org/W6754645375","https://openalex.org/W6773080328","https://openalex.org/W6846337460","https://openalex.org/W6861731181"],"related_works":["https://openalex.org/W2501594388","https://openalex.org/W2381411913","https://openalex.org/W2087331387","https://openalex.org/W4321151660","https://openalex.org/W4367000426","https://openalex.org/W2006060538","https://openalex.org/W4386047771","https://openalex.org/W2107708607","https://openalex.org/W3127908425","https://openalex.org/W4287332487"],"abstract_inverted_index":{"Procedural":[0],"Content":[1],"Generation":[2],"via":[3],"Reinforcement":[4],"Learning":[5],"(PCGRL)":[6],"has":[7,63],"been":[8,66],"introduced":[9],"as":[10,30,171],"a":[11,24,31,43],"means":[12],"by":[13,54],"which":[14],"controllable":[15],"designer":[16],"agents":[17],"can":[18],"be":[19],"trained":[20],"based":[21],"only":[22],"on":[23,97,188],"set":[25,45],"of":[26,46,58,77,90,109,167,174,182],"computable":[27],"metrics":[28],"acting":[29],"proxy":[32],"for":[33,48,138,153,156],"the":[34,55,98,106,179],"level\u2019s":[35],"quality":[36],"and":[37,62,92,115,144,164,193],"key":[38,126],"characteristics.":[39],"While":[40],"PCGRL":[41,82],"offers":[42],"unique":[44],"affordances":[47],"game":[49,169],"designers,":[50,158],"it":[51],"is":[52],"constrained":[53],"compute-intensive":[56],"process":[57],"training":[59,121],"RL":[60,113],"agents,":[61],"so":[64,86],"far":[65],"limited":[67],"to":[68],"generating":[69],"relatively":[70],"small":[71],"levels.":[72],"To":[73,177],"address":[74],"this":[75,132],"issue":[76],"scale,":[78],"we":[79,159,185],"implement":[80],"several":[81,125],"environments":[83],"in":[84,95,101,118,131],"Jax":[85],"that":[87,195],"all":[88],"aspects":[89],"learning":[91],"simulation":[93],"happen":[94],"parallel":[96],"GPU,":[99],"resulting":[100,117],"faster":[102],"environment":[103],"simulation;":[104],"removing":[105],"CPU-GPU":[107],"transfer":[108],"information":[110],"bottleneck":[111],"during":[112],"training;":[114],"ultimately":[116],"significantly":[119],"improved":[120],"speed.":[122],"We":[123],"replicate":[124],"results":[127],"from":[128],"prior":[129],"works":[130],"new":[133],"framework,":[134],"letting":[135],"models":[136,187],"train":[137],"much":[139],"longer":[140],"than":[141],"previously":[142],"studied,":[143],"evaluating":[145],"their":[146],"behavior":[147],"after":[148],"1":[149],"billion":[150],"timesteps.":[151],"Aiming":[152],"greater":[154],"control":[155],"human":[157],"introduce":[160],"randomized":[161],"level":[162],"sizes":[163,198],"frozen":[165],"\u201cpinpoints\u201d":[166],"pivotal":[168],"tiles":[170],"further":[172],"ways":[173],"countering":[175],"overfitting.":[176],"test":[178],"generalization":[180],"ability":[181],"learned":[183],"generators,":[184],"evaluate":[186],"large,":[189],"out-of-distribution":[190],"map":[191],"sizes,":[192],"find":[194],"partial":[196],"observation":[197],"learn":[199],"more":[200],"robust":[201],"design":[202],"strategies.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}