{"id":"https://openalex.org/W3129896193","doi":"https://doi.org/10.1109/iros45743.2020.9341021","title":"An Online Training Method for Augmenting MPC with Deep Reinforcement Learning","display_name":"An Online Training Method for Augmenting MPC with Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3129896193","doi":"https://doi.org/10.1109/iros45743.2020.9341021","mag":"3129896193"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011177211","display_name":"Guillaume Bellegarda","orcid":"https://orcid.org/0000-0001-5809-3340"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guillaume Bellegarda","raw_affiliation_strings":["University of California at Santa Barbara (UCSB),Robotics Laboratory,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara (UCSB),Robotics Laboratory,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071708309","display_name":"Katie Byl","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katie Byl","raw_affiliation_strings":["University of California at Santa Barbara (UCSB),Robotics Laboratory,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara (UCSB),Robotics Laboratory,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011177211"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":1.3256,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85303802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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":0.9994000196456909,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.835615873336792},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7795682549476624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7592923641204834},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.63239586353302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5680468082427979},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.492861270904541},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.48263224959373474},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4605841040611267},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.4122082591056824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4096764624118805},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.35862743854522705},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2600749731063843}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.835615873336792},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7795682549476624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592923641204834},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.63239586353302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5680468082427979},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.492861270904541},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.48263224959373474},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4605841040611267},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.4122082591056824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4096764624118805},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.35862743854522705},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2600749731063843},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1569657508","https://openalex.org/W1777239053","https://openalex.org/W1967821692","https://openalex.org/W2098284983","https://openalex.org/W2104733512","https://openalex.org/W2113115376","https://openalex.org/W2114280243","https://openalex.org/W2123871098","https://openalex.org/W2144351850","https://openalex.org/W2295431040","https://openalex.org/W2575705757","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2738778707","https://openalex.org/W2740828027","https://openalex.org/W2795561664","https://openalex.org/W2842089854","https://openalex.org/W2907537824","https://openalex.org/W2911087563","https://openalex.org/W2963165111","https://openalex.org/W2963184621","https://openalex.org/W2963184939","https://openalex.org/W2963339188","https://openalex.org/W2963355572","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3011481717","https://openalex.org/W3037207827","https://openalex.org/W3090895297","https://openalex.org/W4230405224","https://openalex.org/W6627932998","https://openalex.org/W6634230617","https://openalex.org/W6638088447","https://openalex.org/W6674909112","https://openalex.org/W6675999342","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6755864697","https://openalex.org/W6757380569","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4399671601","https://openalex.org/W1992962589","https://openalex.org/W3032871857","https://openalex.org/W1743191351","https://openalex.org/W3104633800","https://openalex.org/W3023567978","https://openalex.org/W3044778482","https://openalex.org/W3040494141","https://openalex.org/W2003479292","https://openalex.org/W3135469233"],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"both":[2],"in":[3,96,141,192],"reinforcement":[4],"learning":[5,20],"and":[6,44,65,71,84,132],"trajectory":[7],"optimization":[8,56],"have":[9,86],"made":[10],"significant":[11],"advances":[12],"towards":[13],"real":[14],"world":[15],"robotic":[16],"system":[17,198],"deployment.":[18],"Reinforcement":[19],"(RL)":[21],"can":[22],"be":[23],"applied":[24],"to":[25,47,103,179,199],"many":[26],"problems":[27],"without":[28],"needing":[29],"any":[30,49,139],"modeling":[31],"or":[32,153],"intuition":[33],"about":[34,51],"the":[35,38,45,52,59,79,105,126,142,147,160,197],"system,":[36],"at":[37,138],"cost":[39],"of":[40,125,173,182],"high":[41,206],"sample":[42,119],"complexity":[43,120],"inability":[46],"prove":[48],"metrics":[50],"learned":[53],"policies.":[54],"Trajectory":[55],"(TO)":[57],"on":[58,68,171],"other":[60],"hand":[61],"allows":[62],"for":[63,91,94],"stability":[64],"robustness":[66],"analyses":[67],"generated":[69],"motions":[70],"trajectories,":[72],"but":[73],"is":[74,169],"only":[75],"as":[76,78,150,188,190],"good":[77],"often":[80],"over-simplified":[81],"derived":[82],"model,":[83],"may":[85],"prohibitively":[87],"expensive":[88],"computation":[89],"times":[90],"real-time":[92,129],"control,":[93,131],"example":[95],"contact":[97],"rich":[98],"environments.":[99],"This":[100,167],"paper":[101],"seeks":[102],"combine":[104],"benefits":[106],"from":[107],"these":[108],"two":[109],"areas":[110],"while":[111,157,204],"mitigating":[112],"their":[113],"drawbacks":[114],"by":[115,121,145],"(1)":[116],"decreasing":[117],"RL":[118],"using":[122,146],"existing":[123],"knowledge":[124],"problem":[127],"with":[128,164],"optimal":[130],"(2)":[133],"allowing":[134],"online":[135],"policy":[136,163],"deployment":[137],"point":[140],"training":[143],"process":[144],"TO":[148],"(MPC)":[149],"a":[151,176,180],"baseline":[152],"worst-case":[154],"scenario":[155],"action,":[156],"continuously":[158],"improving":[159],"combined":[161],"learned-optimized":[162],"deep":[165],"RL.":[166],"method":[168],"evaluated":[170],"tasks":[172],"successively":[174],"navigating":[175],"car":[177],"model":[178],"series":[181],"goal":[183],"destinations":[184],"over":[185],"slippery":[186],"terrains":[187],"fast":[189],"possible,":[191],"which":[193],"drifting":[194],"will":[195],"allow":[196],"more":[200],"quickly":[201],"change":[202],"directions":[203],"maintaining":[205],"speeds.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}