{"id":"https://openalex.org/W4387171239","doi":"https://doi.org/10.3233/faia230588","title":"Task-Prompt Generalised World Model in Multi-Environment Offline Reinforcement Learning","display_name":"Task-Prompt Generalised World Model in Multi-Environment Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171239","doi":"https://doi.org/10.3233/faia230588"},"language":"en","primary_location":{"id":"doi:10.3233/faia230588","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230588","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230588","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230588","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012772278","display_name":"Xuantang Xiong","orcid":"https://orcid.org/0000-0001-8824-1324"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuantang Xiong","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045700877","display_name":"Linghui Meng","orcid":"https://orcid.org/0000-0001-5915-4395"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghui Meng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076546255","display_name":"Jingqing Ruan","orcid":"https://orcid.org/0000-0002-4857-9053"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqing Ruan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Future Technology, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102868080","display_name":"Qingyang Zhang","orcid":"https://orcid.org/0000-0003-3362-6416"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Future Technology, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018970859","display_name":"Guoqi Li","orcid":"https://orcid.org/0000-0002-8994-431X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqi Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684094","display_name":"Dengpeng Xing","orcid":"https://orcid.org/0000-0002-8251-9118"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengpeng Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4966,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84490877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9070000052452087,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8756721019744873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7608683109283447},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6346302032470703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5657704472541809},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4812633693218231},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.46569690108299255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45674270391464233},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.44809770584106445},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09083858132362366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0686732828617096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8756721019744873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608683109283447},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6346302032470703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5657704472541809},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4812633693218231},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.46569690108299255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45674270391464233},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44809770584106445},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09083858132362366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0686732828617096},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230588","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230588","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230588","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230588","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230588","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230588","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4102930997","display_name":null,"funder_award_id":"62073324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8294312625","display_name":null,"funder_award_id":"XDA27030300","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171239.pdf","grobid_xml":"https://content.openalex.org/works/W4387171239.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1835900096","https://openalex.org/W2102928860","https://openalex.org/W2113065326","https://openalex.org/W2117629901","https://openalex.org/W2138909795","https://openalex.org/W2158782408","https://openalex.org/W2772709170","https://openalex.org/W2795843265","https://openalex.org/W2805762288","https://openalex.org/W2900152462","https://openalex.org/W2904453761","https://openalex.org/W2923762280","https://openalex.org/W2947150733","https://openalex.org/W2950624398","https://openalex.org/W2954142106","https://openalex.org/W2989847975","https://openalex.org/W2992977009","https://openalex.org/W2995298643","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3025660841","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3038270013","https://openalex.org/W3048811857","https://openalex.org/W3118210634","https://openalex.org/W3130177876","https://openalex.org/W3169291081","https://openalex.org/W3183048323","https://openalex.org/W3185341429","https://openalex.org/W3201700917","https://openalex.org/W3205068155","https://openalex.org/W4221146510","https://openalex.org/W4283701713","https://openalex.org/W4287083725","https://openalex.org/W4287689437","https://openalex.org/W4287750003","https://openalex.org/W4287779179","https://openalex.org/W4288289109","https://openalex.org/W4288319859","https://openalex.org/W4289294484","https://openalex.org/W4297801719","https://openalex.org/W4298206671","https://openalex.org/W4307314911","https://openalex.org/W4307868887","https://openalex.org/W4310435735","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,87],"(RL)":[3],"circumvents":[4],"costly":[5],"interactions":[6],"with":[7],"the":[8,24,38,93,101,132,153,157,162],"environment":[9],"by":[10,92],"utilising":[11],"historical":[12],"trajectories.":[13],"Incorporating":[14],"a":[15,60,68,82,119,122,127,137],"world":[16,70,159],"model":[17,71,141],"into":[18],"this":[19,56,113],"method":[20],"could":[21],"substantially":[22],"enhance":[23],"transfer":[25],"performance":[26,111],"of":[27,44,95,156],"various":[28],"tasks":[29],"without":[30],"expensive":[31],"calculations":[32],"from":[33,41,75],"scratch.":[34],"However,":[35],"due":[36],"to":[37,65,145,151],"complexity":[39],"arising":[40],"different":[42,89],"types":[43],"generalisation,":[45],"previous":[46,169],"works":[47],"have":[48],"focused":[49],"almost":[50],"exclusively":[51],"on":[52],"single-environment":[53],"tasks.":[54,90],"In":[55],"study,":[57],"we":[58,99],"introduce":[59],"multi-environment":[61,174],"offline":[62,170],"RL":[63,171],"setting":[64],"investigate":[66],"whether":[67],"generalised":[69,123,133,158],"can":[72],"be":[73],"learned":[74],"large,":[76],"diverse":[77],"datasets":[78],"and":[79,126,142],"serve":[80],"as":[81,136],"good":[83],"surrogate":[84],"for":[85],"policy":[86],"in":[88,112,173],"Inspired":[91],"success":[94],"multi-task":[96],"prompt":[97],"methods,":[98],"propose":[100],"Task-prompt":[102],"Generalised":[103],"World":[104],"Model":[105],"(TGW)":[106],"framework,":[107],"which":[108],"demonstrates":[109],"notable":[110],"setting.":[114,175],"TGW":[115,150,166],"comprises":[116],"three":[117],"modules:":[118],"task-state":[120],"prompter,":[121],"dynamics":[124,134],"module,":[125],"reward":[128],"module.":[129],"We":[130],"implement":[131],"module":[135],"transformer-based":[138],"recurrent":[139],"state-space":[140],"employ":[143],"prompts":[144],"provide":[146],"task-specific":[147],"instructions,":[148],"enabling":[149],"address":[152],"internal":[154],"stochasticity":[155],"model.":[160],"On":[161],"MuJoCo":[163],"control":[164],"benchmarks,":[165],"significantly":[167],"outperforms":[168],"algorithms":[172]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}