{"id":"https://openalex.org/W3138373469","doi":"https://doi.org/10.1109/icra48506.2021.9561298","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","display_name":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3138373469","doi":"https://doi.org/10.1109/icra48506.2021.9561298","mag":"3138373469"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2103.13842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028301925","display_name":"Andrew S. Morgan","orcid":"https://orcid.org/0000-0002-8558-6236"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew S. Morgan","raw_affiliation_strings":["Yale University,Department of Mechanical Engineering & Materials Science,USA","Yale University,Department of Mechanical Engineering and Materials Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Mechanical Engineering & Materials Science,USA","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Yale University,Department of Mechanical Engineering and Materials Science,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062168764","display_name":"Daljeet Nandha","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daljeet Nandha","raw_affiliation_strings":["Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":[]},{"raw_affiliation_string":"Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgia Chalvatzaki","raw_affiliation_strings":["Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":[]},{"raw_affiliation_string":"Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063752250","display_name":"Carlo D\u2019Eramo","orcid":"https://orcid.org/0000-0003-2712-118X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carlo D'Eramo","raw_affiliation_strings":["Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":[]},{"raw_affiliation_string":"Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004284487","display_name":"Aaron M. Dollar","orcid":"https://orcid.org/0000-0002-2409-4668"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron M. Dollar","raw_affiliation_strings":["Yale University,Department of Mechanical Engineering & Materials Science,USA","Yale University,Department of Mechanical Engineering and Materials Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Mechanical Engineering & Materials Science,USA","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Yale University,Department of Mechanical Engineering and Materials Science,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit&#x00E4;t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":[]},{"raw_affiliation_string":"Technische Universit\u00e4t,Intelligent Autonomous Systems,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6672","last_page":"6678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9945999979972839,"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/T10919","display_name":"Neurological disorders and treatments","score":0.965499997138977,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8727762699127197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7059299349784851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.673453688621521},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6117886304855347},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5769749879837036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5558395385742188},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5073241591453552},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4327346682548523},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1992226243019104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11852666735649109}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8727762699127197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059299349784851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.673453688621521},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6117886304855347},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5769749879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5558395385742188},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5073241591453552},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4327346682548523},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1992226243019104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11852666735649109},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra48506.2021.9561298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"mag:3138373469","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2103.13842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2103.13842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.13842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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-journal"}],"best_oa_location":{"id":"mag:3138373469","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2103.13842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2019366029","https://openalex.org/W2104733512","https://openalex.org/W2105038027","https://openalex.org/W2109944946","https://openalex.org/W2119717200","https://openalex.org/W2121103318","https://openalex.org/W2121863487","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2410617946","https://openalex.org/W2416041116","https://openalex.org/W2565233142","https://openalex.org/W2575705757","https://openalex.org/W2736601468","https://openalex.org/W2738778707","https://openalex.org/W2781726626","https://openalex.org/W2785389871","https://openalex.org/W2787757704","https://openalex.org/W2787938642","https://openalex.org/W2788071227","https://openalex.org/W2859967432","https://openalex.org/W2892230114","https://openalex.org/W2898917980","https://openalex.org/W2904246096","https://openalex.org/W2950564923","https://openalex.org/W2951948137","https://openalex.org/W2962872206","https://openalex.org/W2963017537","https://openalex.org/W2963403593","https://openalex.org/W2963414638","https://openalex.org/W2963960193","https://openalex.org/W2964161785","https://openalex.org/W2970277495","https://openalex.org/W2980297602","https://openalex.org/W3024178066","https://openalex.org/W3031634197","https://openalex.org/W3037207827","https://openalex.org/W3041222106","https://openalex.org/W3099587965","https://openalex.org/W3108175278","https://openalex.org/W3138826070","https://openalex.org/W6638018090","https://openalex.org/W6675604983","https://openalex.org/W6675999342","https://openalex.org/W6676444349","https://openalex.org/W6678367057","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6736742618","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747798087","https://openalex.org/W6748012927","https://openalex.org/W6748519856","https://openalex.org/W6748839928","https://openalex.org/W6751494529","https://openalex.org/W6753183898","https://openalex.org/W6754302822","https://openalex.org/W6754471908","https://openalex.org/W6755864697","https://openalex.org/W6757592117","https://openalex.org/W6763990646","https://openalex.org/W6764053384","https://openalex.org/W6768397756","https://openalex.org/W6768621337","https://openalex.org/W6771656438","https://openalex.org/W6772465816","https://openalex.org/W6780559895","https://openalex.org/W6791573717"],"related_works":["https://openalex.org/W3205868665","https://openalex.org/W2418726961","https://openalex.org/W3089470457","https://openalex.org/W3163621993","https://openalex.org/W3183449150","https://openalex.org/W2959488596","https://openalex.org/W2986925736","https://openalex.org/W3175055627","https://openalex.org/W3164426873","https://openalex.org/W2801182767","https://openalex.org/W2963280855","https://openalex.org/W2967129319","https://openalex.org/W3186035148","https://openalex.org/W3090890719","https://openalex.org/W3017262417","https://openalex.org/W3024201688","https://openalex.org/W3206132287","https://openalex.org/W2760799532","https://openalex.org/W2962759351","https://openalex.org/W2967717386"],"abstract_inverted_index":{"Substantial":[0],"advancements":[1],"to":[2,36,76,84,97,110],"model-based":[3],"reinforcement":[4,55],"learning":[5,108,147],"algorithms":[6],"have":[7],"been":[8],"impeded":[9],"by":[10,14,45,143],"the":[11,15,37,95,120],"model-bias":[12],"induced":[13],"collected":[16],"data,":[17],"which":[18],"generally":[19,137],"hurts":[20],"performance.":[21],"Meanwhile,":[22],"their":[23],"inherent":[24],"sample":[25],"efficiency":[26],"warrants":[27],"utility":[28],"for":[29,125,146],"most":[30],"robot":[31,38],"applications,":[32],"limiting":[33],"potential":[34],"damage":[35],"and":[39,51,114,141,156,164],"its":[40,91],"environment":[41],"during":[42],"training.":[43,127],"Inspired":[44],"information":[46],"theoretic":[47],"model":[48,69,78],"predictive":[49,70],"control":[50],"advances":[52],"in":[53],"deep":[54],"learning,":[56,87],"we":[57],"introduce":[58],"Model":[59],"Predictive":[60],"Actor-Critic":[61],"(MoPAC)<sup>&#x2020;</sup>,":[62],"a":[63,149],"hybrid":[64],"model-based/model-free":[65],"method":[66,136],"that":[67,160],"combines":[68],"rollouts":[71],"with":[72,119],"policy":[73,86],"optimization":[74],"as":[75],"mitigate":[77],"bias.":[79],"MoPAC":[80,145],"leverages":[81],"optimal":[82,106],"trajectories":[83],"guide":[85],"but":[88],"explores":[89],"via":[90],"model-free":[92],"method,":[93],"allowing":[94],"algorithm":[96],"learn":[98],"more":[99],"expressive":[100],"dynamics":[101],"models.":[102],"This":[103],"combination":[104],"guarantees":[105],"skill":[107],"up":[109],"an":[111,168],"approximation":[112],"error":[113],"reduces":[115],"necessary":[116],"physical":[117,150],"interaction":[118],"environment,":[121],"making":[122],"it":[123],"suitable":[124],"real-robot":[126],"We":[128],"provide":[129],"extensive":[130],"results":[131],"showcasing":[132],"how":[133],"our":[134],"proposed":[135],"outperforms":[138],"current":[139],"state-of-the-art":[140],"conclude":[142],"evaluating":[144],"on":[148],"robotic":[151],"hand":[152],"performing":[153],"valve":[154],"rotation":[155],"finger":[157],"gaiting&#x2013;a":[158],"task":[159],"requires":[161],"grasping,":[162],"manipulation,":[163],"then":[165],"regrasping":[166],"of":[167],"object.":[169]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}