{"id":"https://openalex.org/W3113244285","doi":"https://doi.org/10.1109/cdc45484.2021.9683134","title":"Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning","display_name":"Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3113244285","doi":"https://doi.org/10.1109/cdc45484.2021.9683134","mag":"3113244285"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683134","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.09156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083548887","display_name":"Nathan Lambert","orcid":"https://orcid.org/0000-0002-9997-6817"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Lambert","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065035597","display_name":"Albert Wilcox","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Wilcox","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077132735","display_name":"Howard Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Zhang","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085143303","display_name":"Kristofer S. J. Pister","orcid":"https://orcid.org/0000-0002-8108-2102"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristofer S. J. Pister","raw_affiliation_strings":["University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering and Computer Sciences,Berkeley,USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002235575","display_name":"Roberto Calandra","orcid":"https://orcid.org/0000-0001-9430-8433"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Calandra","raw_affiliation_strings":["Facebook AI Research,Menlo Park,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research,Menlo Park,CA,USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5073,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64075786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2880","last_page":"2887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9749000072479248,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8406846523284912},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7366635799407959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6627868413925171},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6132523417472839},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.6018269062042236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5394149422645569},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.514337420463562},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4467768669128418},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4397764801979065},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3715834617614746},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3358005881309509},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19056686758995056},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13522717356681824}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8406846523284912},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7366635799407959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6627868413925171},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6132523417472839},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.6018269062042236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5394149422645569},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.514337420463562},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4467768669128418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4397764801979065},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3715834617614746},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3358005881309509},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19056686758995056},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13522717356681824},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C74902906","wikidata":"https://www.wikidata.org/wiki/Q1190858","display_name":"Radiative transfer","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683134","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.09156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.09156","pdf_url":"https://arxiv.org/pdf/2012.09156","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3113244285","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2012.09156.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2012.09156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.09156","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.09156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.09156","pdf_url":"https://arxiv.org/pdf/2012.09156","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3113244285.pdf","grobid_xml":"https://content.openalex.org/works/W3113244285.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W770013183","https://openalex.org/W1505754525","https://openalex.org/W1515569264","https://openalex.org/W1574514837","https://openalex.org/W1973734421","https://openalex.org/W1994275787","https://openalex.org/W1997543377","https://openalex.org/W2015121126","https://openalex.org/W2036101221","https://openalex.org/W2037629065","https://openalex.org/W2073787051","https://openalex.org/W2076337359","https://openalex.org/W2130942839","https://openalex.org/W2140135625","https://openalex.org/W2145957964","https://openalex.org/W2158782408","https://openalex.org/W2268617045","https://openalex.org/W2346505884","https://openalex.org/W2738778707","https://openalex.org/W2758653969","https://openalex.org/W2771401938","https://openalex.org/W2795998072","https://openalex.org/W2913465992","https://openalex.org/W2918394844","https://openalex.org/W2947861305","https://openalex.org/W2963238274","https://openalex.org/W2963755523","https://openalex.org/W2963786176","https://openalex.org/W2963796870","https://openalex.org/W2963960193","https://openalex.org/W2964121744","https://openalex.org/W2970277495","https://openalex.org/W2989847975","https://openalex.org/W2998562709","https://openalex.org/W3041842676","https://openalex.org/W3105904426","https://openalex.org/W3107736070","https://openalex.org/W3109483932","https://openalex.org/W3118210634","https://openalex.org/W4240691156","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6680657880","https://openalex.org/W6681672864","https://openalex.org/W6746075849","https://openalex.org/W6751494529","https://openalex.org/W6752307458","https://openalex.org/W6764053384","https://openalex.org/W6772097985","https://openalex.org/W6773636707"],"related_works":["https://openalex.org/W3007848223","https://openalex.org/W3211674297","https://openalex.org/W2994903850","https://openalex.org/W2783813470","https://openalex.org/W3129235266","https://openalex.org/W3039209232","https://openalex.org/W3087741866","https://openalex.org/W3016221005","https://openalex.org/W3153441237","https://openalex.org/W1890959722","https://openalex.org/W3060285331","https://openalex.org/W3012104296","https://openalex.org/W3198728799","https://openalex.org/W3135475255","https://openalex.org/W2912275020","https://openalex.org/W2892836772","https://openalex.org/W2899347851","https://openalex.org/W3135395562","https://openalex.org/W1979139238","https://openalex.org/W3205682882"],"abstract_inverted_index":{"Accurately":[0],"predicting":[1],"the":[2,36,104,107,134,154],"dynamics":[3,21],"of":[4,150],"robotic":[5,117],"systems":[6],"is":[7,22,46],"crucial":[8],"for":[9,152,157],"model-based":[10],"control":[11,97],"and":[12,30,96,101,115,133],"reinforcement":[13],"learning.":[14],"The":[15],"most":[16],"common":[17],"way":[18],"to":[19,33,48,66,72,136],"estimate":[20],"by":[23],"fitting":[24],"a":[25,63,82,92,148],"one-step":[26],"ahead":[27],"prediction":[28,52,143],"model":[29,87,156],"using":[31,153],"it":[32],"recursively":[34],"propagate":[35],"predicted":[37],"state":[38,105],"distribution":[39],"over":[40],"long":[41,127],"horizons.":[42],"Unfortunately,":[43],"this":[44,59],"approach":[45],"known":[47],"compound":[49],"even":[50],"small":[51],"errors,":[53],"making":[54],"long-term":[55],"predictions":[56],"inaccurate.":[57],"In":[58],"paper,":[60],"we":[61,80,145],"propose":[62],"new":[64],"parametrization":[65],"supervised":[67],"learning":[68],"on":[69],"state-action":[70],"data":[71],"stably":[73],"predict":[74,137],"at":[75,106],"longer":[76],"horizons":[77],"\u2013":[78],"that":[79,120],"call":[81],"trajectory-based":[83,86,121,155],"model.":[84],"This":[85],"takes":[88],"an":[89],"initial":[90],"state,":[91],"future":[93,108],"time":[94,109],"index,":[95],"parameters":[98],"as":[99],"inputs,":[100],"directly":[102],"predicts":[103],"index.":[110],"Experimental":[111],"results":[112],"in":[113],"simulated":[114],"real-world":[116],"tasks":[118],"show":[119],"models":[122],"yield":[123],"significantly":[124],"more":[125],"accurate":[126],"term":[128],"predictions,":[129],"improved":[130,142],"sample":[131],"efficiency,":[132],"ability":[135],"task":[138],"reward.":[139],"With":[140],"these":[141],"properties,":[144],"conclude":[146],"with":[147],"demonstration":[149],"methods":[151],"control.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}