{"id":"https://openalex.org/W4225846751","doi":"https://doi.org/10.1109/icra46639.2022.9812089","title":"Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning","display_name":"Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4225846751","doi":"https://doi.org/10.1109/icra46639.2022.9812089"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812089","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mpra.ub.uni-muenchen.de/76464/9/MPRA_paper_76464.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083595150","display_name":"Utkarsh A. Mishra","orcid":"https://orcid.org/0000-0002-4977-5187"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Utkarsh A. Mishra","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038004412","display_name":"Soumya R. Samineni","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumya R. Samineni","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011871299","display_name":"Prakhar Goel","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]},{"id":"https://openalex.org/I213512949","display_name":"T A Pai Management Institute","ror":"https://ror.org/05saacc29","country_code":"IN","type":"education","lineage":["https://openalex.org/I213512949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prakhar Goel","raw_affiliation_strings":["Manipal Institute of Technology,Electronics and Communication Engineering Department,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal Institute of Technology,Electronics and Communication Engineering Department,India","institution_ids":["https://openalex.org/I164861460","https://openalex.org/I213512949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018569906","display_name":"Chandravaran Kunjeti","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chandravaran Kunjeti","raw_affiliation_strings":["National Institute of Technology,Electronics and Communication Engineering Department,Karnataka,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Electronics and Communication Engineering Department,Karnataka,India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046489967","display_name":"Himanshu Lodha","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshu Lodha","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019518752","display_name":"Aman Singh","orcid":"https://orcid.org/0000-0002-0185-0221"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aman Singh","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011144018","display_name":"Aditya Sagi","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Sagi","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038163398","display_name":"Shalabh Bhatnagar","orcid":"https://orcid.org/0000-0001-7644-3914"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shalabh Bhatnagar","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084523677","display_name":"Shishir Kolathaya","orcid":"https://orcid.org/0000-0001-8689-2318"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shishir Kolathaya","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1631","last_page":"1637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10821","display_name":"Cardiovascular Function and Risk Factors","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10821","display_name":"Cardiovascular Function and Risk Factors","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"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":0.7782777547836304},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6576945185661316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6560219526290894},{"id":"https://openalex.org/keywords/inner-loop","display_name":"Inner loop","score":0.5522499084472656},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.49663764238357544},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4739637076854706},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.4495599567890167},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4333830177783966},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4199099540710449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4148673713207245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3402325510978699},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.21193304657936096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20840996503829956},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.12457031011581421}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7782777547836304},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6576945185661316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560219526290894},{"id":"https://openalex.org/C58716799","wikidata":"https://www.wikidata.org/wiki/Q6035648","display_name":"Inner loop","level":3,"score":0.5522499084472656},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.49663764238357544},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4739637076854706},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.4495599567890167},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4333830177783966},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4199099540710449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4148673713207245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3402325510978699},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.21193304657936096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20840996503829956},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.12457031011581421},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra46639.2022.9812089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812089","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai::76464","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/76464/9/MPRA_paper_76464.pdf","source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai::76464","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/76464/9/MPRA_paper_76464.pdf","source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310071","display_name":"Indian Institute of Science","ror":"https://ror.org/04dese585"},{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"},{"id":"https://openalex.org/F4320334035","display_name":"Robert Bosch Centre for Cyber-Physical Systems, Indian Institute of Science Bangalore","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225846751.pdf","grobid_xml":"https://content.openalex.org/works/W4225846751.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2738778707","https://openalex.org/W2911087563","https://openalex.org/W2962872206","https://openalex.org/W2963411833","https://openalex.org/W3039737909","https://openalex.org/W3093922502","https://openalex.org/W3205868665","https://openalex.org/W4230431917","https://openalex.org/W6675999342","https://openalex.org/W6681812773","https://openalex.org/W6684921986","https://openalex.org/W6747473740","https://openalex.org/W6751494529","https://openalex.org/W6755459763","https://openalex.org/W6755864697","https://openalex.org/W6757380569","https://openalex.org/W6764053384","https://openalex.org/W6767081328","https://openalex.org/W6768397756"],"related_works":["https://openalex.org/W8692371","https://openalex.org/W6083205","https://openalex.org/W2422068","https://openalex.org/W14648536","https://openalex.org/W10980626","https://openalex.org/W6296663","https://openalex.org/W7456372","https://openalex.org/W14518599","https://openalex.org/W10742399","https://openalex.org/W7542396"],"abstract_inverted_index":{"Recent":[0],"works":[1],"in":[2,85,165,175,192],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"combine":[6],"model-free":[7],"(Mf)-RL":[8],"algorithms":[9],"with":[10,46,136],"model-based":[11],"(Mb)-RL":[12],"approaches":[13],"to":[14,75,88],"get":[15],"the":[16,43,50,59,71,91,116,140,149,181,186,193,198],"best":[17],"from":[18],"both:":[19],"asymptotic":[20],"performance":[21],"of":[22,27,80,106,115,148,188],"Mf-RL":[23],"and":[24,110,112,169],"high":[25],"sample-efficiency":[26],"Mb-RL.":[28],"Inspired":[29],"by":[30],"these":[31],"works,":[32],"we":[33],"propose":[34],"a":[35,103,123,166,176],"hierarchical":[36,151],"framework":[37],"that":[38,97,180],"integrates":[39],"online":[40],"learning":[41],"for":[42,49,102,139,162,172],"Mb-trajectory":[44],"optimization":[45],"off-policy":[47],"methods":[48],"Mf-RL.":[51,94],"In":[52],"particular,":[53],"two":[54],"loops":[55],"are":[56,84],"proposed,":[57],"where":[58],"Dynamic":[60],"Mirror":[61],"Descent":[62],"based":[63,108],"Model":[64,127],"Predictive":[65,128],"Control":[66],"(DMD-MPC)":[67],"is":[68,100],"used":[69,87],"as":[70],"inner":[72,141],"loop":[73,93],"Mb-RL":[74,183],"obtain":[76],"an":[77],"optimal":[78],"sequence":[79],"actions.":[81],"These":[82],"actions":[83],"turn":[86],"significantly":[89,184],"accelerate":[90],"outer":[92],"We":[95,120,157,178],"show":[96,145,179],"our":[98],"formulation":[99],"generic":[101],"broad":[104],"class":[105],"MPC":[107],"policies":[109],"objectives,":[111],"includes":[113],"some":[114],"well-known":[117],"Mb-Mf":[118],"approaches.":[119],"finally":[121],"introduce":[122],"new":[124],"algorithm:":[125],"Mirror-Descent":[126],"RL":[129],"(M-DeMoRL),":[130],"which":[131],"uses":[132],"Cross-Entropy":[133],"Method":[134],"(CEM)":[135],"elite":[137],"fractions":[138],"loop.":[142],"Our":[143],"experiments":[144],"faster":[146],"convergence":[147],"proposed":[150,199],"approach":[152],"on":[153],"benchmark":[154],"MuJoCo":[155],"tasks.":[156],"also":[158],"demonstrate":[159],"hardware":[160,170,194],"training":[161,189],"trajectory":[163],"tracking":[164],"2R":[167],"leg,":[168],"transfer":[171],"robust":[173],"walking":[174],"quadruped.":[177],"inner-loop":[182],"decreases":[185],"number":[187],"iterations":[190],"required":[191],"setting,":[195],"thereby":[196],"validating":[197],"approach.":[200]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2022-05-05T00:00:00"}