{"id":"https://openalex.org/W2975112661","doi":"https://doi.org/10.1109/cig.2019.8848075","title":"Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning","display_name":"Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2975112661","doi":"https://doi.org/10.1109/cig.2019.8848075","mag":"2975112661"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2019.8848075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848075","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Games (CoG)","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/A5046008680","display_name":"Yuji Kanagawa","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I165953009","display_name":"Tokyo University of the Arts","ror":"https://ror.org/00y809n33","country_code":"JP","type":"education","lineage":["https://openalex.org/I165953009"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuji Kanagawa","raw_affiliation_strings":["Graduate School of Arts and Sciences, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Arts and Sciences, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I165953009","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103172324","display_name":"Tomoyuki Kaneko","orcid":"https://orcid.org/0000-0001-8051-2388"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyuki Kaneko","raw_affiliation_strings":["Interfaculty Initiative in Information Studies, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Interfaculty Initiative in Information Studies, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046008680"],"corresponding_institution_ids":["https://openalex.org/I165953009","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.443,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86615253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9951000213623047,"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":0.9904999732971191,"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/overfitting","display_name":"Overfitting","score":0.9032204151153564},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8967351913452148},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8803189992904663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506102323532104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6780330538749695},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6711018681526184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5196424722671509},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.466467022895813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07532376050949097}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9032204151153564},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8967351913452148},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8803189992904663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506102323532104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6780330538749695},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6711018681526184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5196424722671509},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.466467022895813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07532376050949097},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2019.8848075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848075","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W22861983","https://openalex.org/W1836465849","https://openalex.org/W1959608418","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2749928749","https://openalex.org/W2753738274","https://openalex.org/W2781726626","https://openalex.org/W2787666871","https://openalex.org/W2797527950","https://openalex.org/W2893662673","https://openalex.org/W2903181768","https://openalex.org/W2914898814","https://openalex.org/W2953722837","https://openalex.org/W2963403143","https://openalex.org/W2963611966","https://openalex.org/W2963985863","https://openalex.org/W2964043796","https://openalex.org/W2966556569","https://openalex.org/W2968983352","https://openalex.org/W3037207827","https://openalex.org/W3103780890","https://openalex.org/W4297744728","https://openalex.org/W4297789758","https://openalex.org/W4297797010","https://openalex.org/W6600949241","https://openalex.org/W6638667902","https://openalex.org/W6640963894","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6741977017","https://openalex.org/W6743802245","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6750629867","https://openalex.org/W6752818208","https://openalex.org/W6754629161","https://openalex.org/W6756840741","https://openalex.org/W6765378368","https://openalex.org/W6780225908","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"In":[0,107,146],"this":[1,75],"paper,":[2],"we":[3,90,135,149],"propose":[4,91],"Rogue-Gym,":[5,109,179],"a":[6,97,123,151],"simple":[7],"and":[8,65,158],"classic":[9],"style":[10],"roguelike":[11],"game":[12],"built":[13],"for":[14,45,99,161],"evaluating":[15,100],"generalization":[16,102,139,185],"in":[17,39,69,178],"reinforcement":[18,153],"learning":[19,154],"(RL).":[20],"Combined":[21],"with":[22,57,80,157],"the":[23,62,92,101,128,133,138,176,184],"recent":[24],"progress":[25],"of":[26,94,104,132,141],"deep":[27],"neural":[28],"networks,":[29],"RL":[30,58,105],"has":[31,50],"successfully":[32],"trained":[33,56],"humanlevel":[34],"agents":[35,55,110],"without":[36,159],"human":[37],"knowledge":[38],"many":[40],"games":[41],"such":[42],"as":[43,96],"those":[44],"Atari":[46],"2600.":[47],"However,":[48],"it":[49],"been":[51,85],"pointed":[52],"out":[53],"that":[54,115,137,166],"methods":[59],"often":[60],"overfit":[61],"training":[63],"environment,":[64],"they":[66,121],"work":[67],"poorly":[68],"slightly":[70,182],"different":[71],"environments.":[72],"To":[73],"investigate":[74],"problem,":[76],"some":[77,167],"research":[78],"environments":[79],"procedural":[81],"content":[82],"generation":[83],"have":[84],"proposed.":[86],"Following":[87],"these":[88],"studies,":[89],"use":[93],"roguelikes":[95],"benchmark":[98,140],"ability":[103],"agents.":[106],"our":[108,147],"need":[111],"to":[112,127,170,174],"explore":[113],"dungeons":[114],"are":[116],"structured":[117],"differently":[118],"each":[119],"time":[120],"start":[122],"new":[124],"game.":[125],"Thanks":[126],"very":[129],"diverse":[130],"structures":[131],"dungeons,":[134],"believe":[136],"Rogue-Gym":[142],"is":[143],"sufficiently":[144],"fair.":[145],"experiments,":[148],"evaluate":[150],"standard":[152],"method,":[155],"PPO,":[156],"enhancements":[160,168],"generalization.":[162],"The":[163],"results":[164],"show":[165],"believed":[169],"be":[171],"effective":[172],"fail":[173],"mitigate":[175],"overfitting":[177],"although":[180],"others":[181],"improve":[183],"ability.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}