{"id":"https://openalex.org/W3093820981","doi":"https://doi.org/10.1109/cog47356.2020.9231622","title":"Deep Reinforcement Learning with Transformers for Text Adventure Games","display_name":"Deep Reinforcement Learning with Transformers for Text Adventure Games","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3093820981","doi":"https://doi.org/10.1109/cog47356.2020.9231622","mag":"3093820981"},"language":"en","primary_location":{"id":"doi:10.1109/cog47356.2020.9231622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231622","pdf_url":null,"source":{"id":"https://openalex.org/S4306498668","display_name":"2020 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":"2020 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/A5057243649","display_name":"Yunqiu Xu","orcid":"https://orcid.org/0000-0002-1721-764X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yunqiu Xu","raw_affiliation_strings":["Centre for Artificial Intelligence, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069988750","display_name":"Ling Chen","orcid":"https://orcid.org/0000-0002-6468-5729"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ling Chen","raw_affiliation_strings":["Centre for Artificial Intelligence, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400497","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0003-0793-9187"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["Tencent Robotics X"],"affiliations":[{"raw_affiliation_string":"Tencent Robotics X","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762359","display_name":"Yang Wang","orcid":"https://orcid.org/0009-0000-7042-3330"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education), Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education), Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438525","display_name":"Chengqi Zhang","orcid":"https://orcid.org/0000-0001-5715-7154"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chengqi Zhang","raw_affiliation_strings":["Centre for Artificial Intelligence, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057243649"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":1.5647,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.86020391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9973000288009644,"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":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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":0.9940000176429749,"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/transformer","display_name":"Transformer","score":0.7690147161483765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7535861730575562},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.713160514831543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5751979351043701},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3841431736946106},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3410889208316803},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1432861089706421},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11982423067092896},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0808003842830658}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7690147161483765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7535861730575562},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.713160514831543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5751979351043701},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3841431736946106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3410889208316803},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1432861089706421},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11982423067092896},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0808003842830658}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog47356.2020.9231622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231622","pdf_url":null,"source":{"id":"https://openalex.org/S4306498668","display_name":"2020 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":"2020 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1026270304","https://openalex.org/W1934909785","https://openalex.org/W2064675550","https://openalex.org/W2121092017","https://openalex.org/W2173248099","https://openalex.org/W2194775991","https://openalex.org/W2310425190","https://openalex.org/W2604468927","https://openalex.org/W2614188047","https://openalex.org/W2787501667","https://openalex.org/W2810305479","https://openalex.org/W2810346659","https://openalex.org/W2866343820","https://openalex.org/W2885238722","https://openalex.org/W2891217993","https://openalex.org/W2896457183","https://openalex.org/W2902391430","https://openalex.org/W2907502844","https://openalex.org/W2909335861","https://openalex.org/W2912937857","https://openalex.org/W2950621961","https://openalex.org/W2950670227","https://openalex.org/W2954579883","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963696295","https://openalex.org/W2963771109","https://openalex.org/W2963864421","https://openalex.org/W2963871073","https://openalex.org/W2964179661","https://openalex.org/W2964915587","https://openalex.org/W2967987061","https://openalex.org/W2970393539","https://openalex.org/W2975227997","https://openalex.org/W2980433389","https://openalex.org/W2980473882","https://openalex.org/W2985293964","https://openalex.org/W2996428491","https://openalex.org/W2996681978","https://openalex.org/W2998557583","https://openalex.org/W3000752281","https://openalex.org/W3035435378","https://openalex.org/W3101555782","https://openalex.org/W3194382904","https://openalex.org/W4298857966","https://openalex.org/W4385245566","https://openalex.org/W6626481562","https://openalex.org/W6637967152","https://openalex.org/W6677939520","https://openalex.org/W6684921986","https://openalex.org/W6739901393","https://openalex.org/W6747943641","https://openalex.org/W6752381818","https://openalex.org/W6753640285","https://openalex.org/W6755207826","https://openalex.org/W6755612348","https://openalex.org/W6757797181","https://openalex.org/W6758315252","https://openalex.org/W6758872177","https://openalex.org/W6767047803","https://openalex.org/W6768021236","https://openalex.org/W6768238010","https://openalex.org/W6768810269","https://openalex.org/W6768890005","https://openalex.org/W6772190580","https://openalex.org/W6780225908"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,65],"study":[4],"transformers":[5],"for":[6,34],"text-based":[7],"games.":[8,110,122],"As":[9],"a":[10,29,49,67,106,118],"promising":[11],"replacement":[12],"of":[13,52,108,120],"recurrent":[14],"modules":[15],"in":[16,117],"Natural":[17],"Language":[18],"Processing":[19],"(NLP)":[20],"tasks,":[21],"the":[22,38],"transformer":[23,40],"architecture":[24],"could":[25],"be":[26],"treated":[27],"as":[28],"powerful":[30],"state":[31],"representation":[32,71],"generator":[33,72],"reinforcement":[35],"learning.":[36],"However,":[37],"vanilla":[39],"is":[41],"neither":[42],"effective":[43],"nor":[44],"efficient":[45],"to":[46],"learn":[47],"with":[48,74,96],"huge":[50],"amount":[51],"weight":[53,78],"parameters.":[54],"Unlike":[55],"existing":[56],"research":[57],"that":[58,87],"encodes":[59],"states":[60],"using":[61],"LSTMs":[62],"or":[63],"GRUs,":[64],"develop":[66],"novel":[68],"lightweight":[69],"transformer-based":[70],"featured":[73],"reordered":[75],"layer":[76],"normalization,":[77],"sharing":[79],"and":[80],"block-wise":[81],"aggregation.":[82],"The":[83],"experimental":[84],"results":[85],"show":[86],"our":[88,112],"proposed":[89],"model":[90,113],"not":[91],"only":[92],"solves":[93],"single":[94],"games":[95],"much":[97],"fewer":[98],"interactions,":[99],"but":[100],"also":[101],"achieves":[102],"better":[103],"generalization":[104],"on":[105],"set":[107],"unseen":[109],"Furthermore,":[111],"outperforms":[114],"state-of-the-art":[115],"agents":[116],"variety":[119],"man-made":[121]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}