{"id":"https://openalex.org/W4387529488","doi":"https://doi.org/10.1007/s40747-023-01247-5","title":"Data-efficient model-based reinforcement learning with trajectory discrimination","display_name":"Data-efficient model-based reinforcement learning with trajectory discrimination","publication_year":2023,"publication_date":"2023-10-11","ids":{"openalex":"https://openalex.org/W4387529488","doi":"https://doi.org/10.1007/s40747-023-01247-5"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-023-01247-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01247-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01247-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01247-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109998903","display_name":"Tuo Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tuo Qu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, No.19 Xinjiekou Outer Street, 100875, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, No.19 Xinjiekou Outer Street, 100875, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084694395","display_name":"Fuqing Duan","orcid":"https://orcid.org/0000-0002-3849-8532"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuqing Duan","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, No.19 Xinjiekou Outer Street, 100875, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, No.19 Xinjiekou Outer Street, 100875, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012644","display_name":"Junge Zhang","orcid":"https://orcid.org/0000-0002-9970-394X"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junge Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, No.95 Zhongguancun East Road, 100190, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, No.95 Zhongguancun East Road, 100190, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074387543","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-7684-7342"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["School of Systems Science, Beijing Normal University, No.19 Xinjiekou Outer Street, 100875, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Systems Science, Beijing Normal University, No.19 Xinjiekou Outer Street, 100875, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111794931","display_name":"Wenzhen Huang","orcid":"https://orcid.org/0000-0003-0454-7516"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhen Huang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, No.95 Zhongguancun East Road, 100190, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, No.95 Zhongguancun East Road, 100190, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109998903"],"corresponding_institution_ids":["https://openalex.org/I25254941"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.3521,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6667574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"10","issue":"2","first_page":"1927","last_page":"1936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9890000224113464,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9312011003494263},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7795252799987793},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7718786001205444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6913775205612183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6680149435997009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5042494535446167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48358792066574097},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43611425161361694}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9312011003494263},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7795252799987793},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7718786001205444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913775205612183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6680149435997009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5042494535446167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48358792066574097},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43611425161361694},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-023-01247-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01247-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01247-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2064579341e94e31a96af8d2a19badce","is_oa":true,"landing_page_url":"https://doaj.org/article/2064579341e94e31a96af8d2a19badce","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 2, Pp 1927-1936 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-023-01247-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01247-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01247-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387529488.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1980035368","https://openalex.org/W1981276685","https://openalex.org/W2268617045","https://openalex.org/W2572640103","https://openalex.org/W2989847975","https://openalex.org/W2990138404","https://openalex.org/W3118210634","https://openalex.org/W3159481202","https://openalex.org/W4226249635","https://openalex.org/W4283741465","https://openalex.org/W4386083023","https://openalex.org/W6601939488","https://openalex.org/W6769122368"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2964074194","https://openalex.org/W2057775761","https://openalex.org/W2985313479"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"reinforcement":[2,22,33,63,73],"learning":[3,23,34,74],"has":[4,57],"always":[5],"been":[6],"used":[7],"to":[8,96,114,123],"solve":[9,36],"high-dimensional":[10,29],"complex":[11,30],"sequential":[12],"decision":[13],"problems.":[14,31],"However,":[15],"one":[16],"of":[17,87,105],"the":[18,37,45,50,85,97,103,111,116,121,134,138,148],"biggest":[19],"challenges":[20],"for":[21,28],"is":[24,47],"sample":[25,149],"efficiency,":[26],"especially":[27],"Model-based":[32],"can":[35],"problem":[38],"with":[39,79,137],"a":[40,70,93,129],"learned":[41],"world":[42,52,98,139],"model,":[43,53,99],"but":[44],"performance":[46,60,154],"limited":[48],"by":[49,91],"imperfect":[51],"so":[54],"it":[55],"usually":[56],"worse":[58],"approximate":[59],"than":[61],"model-free":[62],"learning.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,119],"propose":[69],"novel":[71],"model-based":[72],"algorithm":[75],"called":[76],"World":[77],"Model":[78],"Trajectory":[80],"Discrimination":[81],"(WMTD).":[82],"We":[83],"learn":[84],"representation":[86],"temporal":[88],"dynamics":[89],"information":[90],"adding":[92],"trajectory":[94,112,130],"discriminator":[95,113,131],"and":[100,127,151],"then":[101],"compute":[102],"weight":[104],"state":[106],"value":[107],"estimation":[108],"based":[109],"on":[110,155],"optimize":[115],"policy.":[117],"Specifically,":[118],"augment":[120],"trajectories":[122],"generate":[124],"negative":[125],"samples":[126],"train":[128],"that":[132,144],"shares":[133],"feature":[135],"extractor":[136],"model.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"our":[145],"method":[146],"improves":[147],"efficiency":[150],"achieves":[152],"state-of-the-art":[153],"DeepMind":[156],"control":[157],"tasks.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}