{"id":"https://openalex.org/W3001182513","doi":"https://doi.org/10.24963/ijcai.2020/207","title":"Exploration Based Language Learning for Text-Based Games","display_name":"Exploration Based Language Learning for Text-Based Games","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3001182513","doi":"https://doi.org/10.24963/ijcai.2020/207","mag":"3001182513"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/207","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/207","pdf_url":"https://www.ijcai.org/proceedings/2020/0207.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0207.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061096363","display_name":"Andrea Madotto","orcid":"https://orcid.org/0000-0002-8672-715X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Andrea Madotto","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026771837","display_name":"Mahdi Namazifar","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]},{"id":"https://openalex.org/I4210158152","display_name":"Universidade de Uberaba","ror":"https://ror.org/05hzgxd58","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210158152"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Mahdi Namazifar","raw_affiliation_strings":["Uber Technologies, Inc","UBER TECHNOLOGIES INC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uber Technologies, Inc","institution_ids":["https://openalex.org/I2946016260"]},{"raw_affiliation_string":"UBER TECHNOLOGIES INC","institution_ids":["https://openalex.org/I4210158152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018598100","display_name":"Joost Huizinga","orcid":"https://orcid.org/0000-0003-0877-3051"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joost Huizinga","raw_affiliation_strings":["UberAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UberAI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028406899","display_name":"Piero Molino","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piero Molino","raw_affiliation_strings":["Uber AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uber AI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033112877","display_name":"Adrien Ecoffet","orcid":"https://orcid.org/0000-0001-9985-365X"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrien Ecoffet","raw_affiliation_strings":["UberAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UberAI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003807260","display_name":"Huaixiu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaixiu Zheng","raw_affiliation_strings":["Google Brain","[Google Brain]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014990977","display_name":"Alexandros Papangelis","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandros Papangelis","raw_affiliation_strings":["UberAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UberAI","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101834699","display_name":"Dian Yu","orcid":"https://orcid.org/0000-0002-8583-8931"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dian Yu","raw_affiliation_strings":["University of California, Davis","Univ. of California Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Univ. of California Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043744102","display_name":"Chandra Khatri","orcid":null},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandra Khatri","raw_affiliation_strings":["Uber"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uber","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":"https://orcid.org/0009-0008-7740-2557"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["Amazon Alexa AI","[Amazon Alexa AI]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Alexa AI]","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.301,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84300039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1488","last_page":"1494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9976000189781189,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7802760601043701},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6968928575515747},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6378555297851562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5848714709281921},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5787937045097351},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5223059058189392},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.47259435057640076},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45000576972961426},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.42228174209594727},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33763229846954346},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10841229557991028},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09505575895309448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802760601043701},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6968928575515747},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6378555297851562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5848714709281921},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5787937045097351},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5223059058189392},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.47259435057640076},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45000576972961426},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.42228174209594727},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33763229846954346},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10841229557991028},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09505575895309448},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.24963/ijcai.2020/207","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/207","pdf_url":"https://www.ijcai.org/proceedings/2020/0207.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.08868","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.08868","pdf_url":"https://arxiv.org/pdf/2001.08868","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-108831","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1045-0823&rft.volume=v. 2021-January&rft.issue=&rft.date=2020&rft.spage=1488&rft.aulast=Madotto&rft.aufirst=A.&rft.atitle=Exploration+based+language+learning+for+text-based+games&rft.title=IJCAI+International+Joint+Conference+on+Artificial+Intelligence","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-108831","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-108831","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.2001.08868","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.08868","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3001182513","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/207","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/207","pdf_url":"https://www.ijcai.org/proceedings/2020/0207.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3001182513.pdf","grobid_xml":"https://content.openalex.org/works/W3001182513.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1810943226","https://openalex.org/W1863227302","https://openalex.org/W1993378086","https://openalex.org/W2000514530","https://openalex.org/W2016589492","https://openalex.org/W2061868368","https://openalex.org/W2130942839","https://openalex.org/W2145339207","https://openalex.org/W2151083897","https://openalex.org/W2154022540","https://openalex.org/W2168359464","https://openalex.org/W2188721763","https://openalex.org/W2250539671","https://openalex.org/W2346736747","https://openalex.org/W2465628802","https://openalex.org/W2593766708","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2782698114","https://openalex.org/W2810305479","https://openalex.org/W2891217993","https://openalex.org/W2899205164","https://openalex.org/W2902391430","https://openalex.org/W2903394565","https://openalex.org/W2904157920","https://openalex.org/W2914261249","https://openalex.org/W2946088105","https://openalex.org/W2948380112","https://openalex.org/W2949801941","https://openalex.org/W2952222085","https://openalex.org/W2954579883","https://openalex.org/W2963771109","https://openalex.org/W2963790038","https://openalex.org/W2967987061","https://openalex.org/W3008890934","https://openalex.org/W3011120880","https://openalex.org/W6650587873"],"related_works":["https://openalex.org/W2803814120","https://openalex.org/W2900172492","https://openalex.org/W2782698114","https://openalex.org/W2123995443","https://openalex.org/W2113363668","https://openalex.org/W2996887765","https://openalex.org/W2084771774","https://openalex.org/W2949801941","https://openalex.org/W2619568925","https://openalex.org/W3091858927","https://openalex.org/W789315506","https://openalex.org/W3000558234","https://openalex.org/W2181388735","https://openalex.org/W152102936","https://openalex.org/W51120195","https://openalex.org/W2040615834","https://openalex.org/W1486652901","https://openalex.org/W3119788022","https://openalex.org/W2900118155","https://openalex.org/W137637974"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"an":[3,56,97,127],"exploration":[4,116,129],"and":[5,34,165],"imitation-learning-based":[6],"agent":[7],"capable":[8],"of":[9,20,105,118,173,176],"state-of-the-art":[10],"performance":[11],"in":[12,46,126,161,171],"playing":[13],"text-based":[14,84,122,163],"computer":[15],"games.":[16,123],"These":[17],"games":[18,68,85,89,196],"are":[19,86,91],"interest":[21],"as":[22,27],"they":[23,41],"can":[24,50,188],"be":[25,51],"seen":[26],"a":[28,43,102,142],"testbed":[29],"for":[30,71,82,120],"language":[31,35],"understanding,":[32],"problem-solving,":[33],"generation":[36],"by":[37,148],"artificial":[38],"agents.":[39],"Moreover,":[40,181],"provide":[42],"learning":[44,72],"setting":[45],"which":[47,139],"these":[48,67,150],"skills":[49],"acquired":[52],"through":[53],"interactions":[54,177],"with":[55,135,178],"environment":[57],"rather":[58],"than":[59,191],"using":[60,198],"fixed":[61],"corpora.":[62],"One":[63],"aspect":[64],"that":[65,90,155,184],"makes":[66],"particularly":[69],"challenging":[70],"agents":[73],"is":[74,167],"the":[75,115,146,174,179,185,202],"combinatorially":[76],"large":[77],"action":[78,98,203],"space.":[79,204],"Existing":[80],"methods":[81],"solving":[83,121,162],"limited":[87],"to":[88,101,113,144,194],"either":[92],"very":[93],"simple":[94],"or":[95],"have":[96],"space":[99],"restricted":[100],"predetermined":[103],"set":[104],"admissible":[106],"actions.":[107],"In":[108],"this":[109,156],"work,":[110],"we":[111,131,140,182],"propose":[112],"use":[114],"approach":[117,157],"Go-Explore":[119],"More":[124],"specifically,":[125],"initial":[128],"phase,":[130],"first":[132],"extract":[133],"trajectories":[134],"high":[136],"rewards,":[137],"after":[138],"train":[141],"policy":[143,187],"solve":[145],"game":[147],"imitating":[149],"trajectories.":[151],"Our":[152],"experiments":[153],"show":[154,183],"outperforms":[158],"existing":[159,192],"solutions":[160,193],"games,":[164],"it":[166],"more":[168],"sample":[169],"efficient":[170],"terms":[172],"number":[175],"environment.":[180],"learned":[186],"generalize":[189],"better":[190],"unseen":[195],"without":[197],"any":[199],"restriction":[200],"on":[201]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}