{"id":"https://openalex.org/W4385570073","doi":"https://doi.org/10.18653/v1/2023.findings-acl.836","title":"Abstract then Play: A Skill-centric Reinforcement Learning Framework for Text-based Games","display_name":"Abstract then Play: A Skill-centric Reinforcement Learning Framework for Text-based Games","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385570073","doi":"https://doi.org/10.18653/v1/2023.findings-acl.836"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.836","pdf_url":"https://aclanthology.org/2023.findings-acl.836.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-acl.836.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081872546","display_name":"Anjie Zhu","orcid":"https://orcid.org/0000-0002-4634-7961"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anjie Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354128","display_name":"Peng-Fei Zhang","orcid":"https://orcid.org/0000-0002-6790-2098"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peng-Fei Zhang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104126346","display_name":"Yi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia","University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":69},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Natural Language Processing","score":0.992,"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/T10028","display_name":"Natural Language Processing","score":0.992,"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":"Visual Question Answering in Images and Videos","score":0.9826,"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"}},{"id":"https://openalex.org/T11574","display_name":"Game Artificial Intelligence Research","score":0.9746,"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/player-modeling","display_name":"Player Modeling","score":0.546051},{"id":"https://openalex.org/keywords/general-game-playing","display_name":"General Game Playing","score":0.544836},{"id":"https://openalex.org/keywords/real-time-strategy-games","display_name":"Real-Time Strategy Games","score":0.530557},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.51991624},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"Visual Question Answering","score":0.519056},{"id":"https://openalex.org/keywords/inverse-dynamics","display_name":"Inverse dynamics","score":0.5153224},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language Understanding","score":0.504018},{"id":"https://openalex.org/keywords/hypersphere","display_name":"Hypersphere","score":0.41939017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79882693},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.65373766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987208},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.54122484},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.51991624},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.5153224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48988312},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46070638},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.45674032},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4419162},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42243484},{"id":"https://openalex.org/C2776562905","wikidata":"https://www.wikidata.org/wiki/Q306610","display_name":"Hypersphere","level":2,"score":0.41939017},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.836","pdf_url":"https://aclanthology.org/2023.findings-acl.836.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.836","pdf_url":"https://aclanthology.org/2023.findings-acl.836.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.69,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1934909785","https://openalex.org/W2145339207","https://openalex.org/W2152670157","https://openalex.org/W2891217993","https://openalex.org/W2963438456","https://openalex.org/W2964179661","https://openalex.org/W2996681978","https://openalex.org/W2996887765","https://openalex.org/W2998557583","https://openalex.org/W3034291030","https://openalex.org/W3035348754","https://openalex.org/W3099204253","https://openalex.org/W3099954076","https://openalex.org/W3103274847","https://openalex.org/W3122177264","https://openalex.org/W3171009994","https://openalex.org/W3177151026","https://openalex.org/W3199912944","https://openalex.org/W3200711617","https://openalex.org/W4224293203","https://openalex.org/W4286901958","https://openalex.org/W4287635137","https://openalex.org/W4287865969","https://openalex.org/W4293469690","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W942984284","https://openalex.org/W2967463586","https://openalex.org/W2921850681","https://openalex.org/W2765830098","https://openalex.org/W2099702253","https://openalex.org/W2069017679","https://openalex.org/W2059484267","https://openalex.org/W2046459260","https://openalex.org/W1971989957","https://openalex.org/W1970780628"],"abstract_inverted_index":{"Text-based":[0],"games":[1],"present":[2],"an":[3,19,91],"exciting":[4],"test-bed":[5],"for":[6],"reinforcement":[7,80],"learning":[8,81],"algorithms":[9],"in":[10,30,90,110,166],"the":[11,26,53,57,63,68,88,103,108,113,124,128,135,161,188,192,195],"natural":[12],"language":[13],"environment.":[14],"In":[15,72],"these":[16],"adventure":[17],"games,":[18],"agent":[20],"must":[21],"learn":[22,95,148],"to":[23,32,51,122,126,138,147,159],"interact":[24],"with":[25,112],"environment":[27,190],"through":[28],"text":[29],"order":[31],"accomplish":[33],"tasks,":[34],"facing":[35],"large":[36],"and":[37,55,105,130,150,153,173,180,191],"combinational":[38],"action":[39,58,89,162],"space":[40],"as":[41,43],"well":[42],"partial":[44],"observability":[45],"issues.":[46],"However,":[47],"existing":[48],"solutions":[49],"fail":[50],"decompose":[52],"task":[54],"abstract":[56],"autonomously,":[59],"which":[60,83],"either":[61],"pre-specify":[62],"subtasks":[64],"or":[65],"pre-train":[66],"on":[67,102,187],"human":[69],"gameplay":[70],"dataset.":[71],"this":[73],"work,":[74],"we":[75,100,118],"introduce":[76,119],"a":[77,96,120,142,154,167],"novel":[78],"skill-centric":[79],"framework,":[82],"is":[84,145,157],"capable":[85],"of":[86,107,171,177],"abstracting":[87],"end-to-end":[92],"manner.":[93],"To":[94],"more":[97,168,174],"disentangled":[98],"skill,":[99],"focus":[101],"informativeness":[104],"distinguishability":[106],"skill":[109,125],"accordance":[111],"information":[114],"bottleneck":[115],"principle.":[116],"Specifically,":[117],"discriminator":[121],"enable":[123],"reflect":[127],"trajectory":[129],"push":[131],"their":[132],"representations":[133,176],"onto":[134],"unit":[136],"hypersphere":[137],"distribute":[139],"uniformly.":[140],"Moreover,":[141],"self-predictive":[143],"mechanism":[144,156],"employed":[146],"inverse":[149],"forward":[151],"dynamics,":[152],"self-recovery":[155],"leveraged":[158],"refine":[160],"representation,":[163],"thus":[164],"resulting":[165],"comprehensive":[169],"perception":[170],"dynamics":[172],"effective":[175],"textual":[178],"state":[179],"action.":[181],"Empirical":[182],"experiments":[183],"are":[184],"carried":[185],"out":[186],"Jericho":[189],"results":[193],"validate":[194],"superiority":[196],"against":[197],"state-of-the-art":[198],"baselines.":[199]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4385570073","counts_by_year":[],"updated_date":"2024-11-15T19:11:06.415022","created_date":"2023-08-05"}
