{"id":"https://openalex.org/W2418627435","doi":"https://doi.org/10.1109/icra.2016.7487756","title":"Autonomous drifting using simulation-aided reinforcement learning","display_name":"Autonomous drifting using simulation-aided reinforcement learning","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2418627435","doi":"https://doi.org/10.1109/icra.2016.7487756","mag":"2418627435"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2016.7487756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","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/A5020653160","display_name":"Mark Cutler","orcid":"https://orcid.org/0000-0002-2823-3223"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Cutler","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020653160"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":5.3233,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.95851795,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5442","last_page":"5448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9879999756813049,"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":0.8640944957733154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7687008380889893},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6517876386642456},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5464963912963867},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5164785385131836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45934849977493286},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.44375765323638916},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3654025197029114},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.35786134004592896},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.335497111082077},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10991346836090088}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8640944957733154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687008380889893},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6517876386642456},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5464963912963867},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5164785385131836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45934849977493286},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.44375765323638916},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3654025197029114},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.35786134004592896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.335497111082077},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10991346836090088},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2016.7487756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1540685400","https://openalex.org/W1587009522","https://openalex.org/W1746819321","https://openalex.org/W1977556410","https://openalex.org/W1977655452","https://openalex.org/W2012204020","https://openalex.org/W2018705428","https://openalex.org/W2023842042","https://openalex.org/W2033800064","https://openalex.org/W2042520683","https://openalex.org/W2089488098","https://openalex.org/W2124770562","https://openalex.org/W2130527887","https://openalex.org/W2132602063","https://openalex.org/W2134491302","https://openalex.org/W2145175815","https://openalex.org/W2204090322","https://openalex.org/W4211049957","https://openalex.org/W6632235069","https://openalex.org/W6655145722"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W4306904969","https://openalex.org/W2144385241","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W1981414187","https://openalex.org/W2889082928"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,13,48,58,62,147],"framework":[3,34,143],"that":[4,54],"combines":[5,35],"simple":[6,49],"and":[7,51,68],"complex":[8,64,73],"continuous":[9],"state-action":[10],"simulators":[11],"with":[12],"real-world":[14],"robot":[15],"to":[16,56,79,100,112,134,151],"efficiently":[17],"find":[18],"good":[19],"control":[20],"policies,":[21],"while":[22],"minimizing":[23,135],"the":[24,30,36,72,81,84,96,101,105,115,123,127,138,159],"number":[25],"of":[26,38,158],"samples":[27,136],"needed":[28],"from":[29,71,126,137],"physical":[31,85,97,139],"robot.":[32],"The":[33,66,107,141],"strengths":[37],"various":[39],"simulation":[40,74],"levels":[41],"by":[42],"first":[43],"finding":[44],"optimal":[45,121],"policies":[46],"in":[47,61,76,83,95,104],"model,":[50],"then":[52],"using":[53],"solution":[55],"initialize":[57],"gradient-based":[59],"learner":[60],"more":[63],"simulation.":[65,106],"policy":[67,118],"transition":[69],"dynamics":[70],"are":[75],"turn":[77],"used":[78,111],"guide":[80],"learning":[82,102,150],"world.":[86,140],"A":[87,156],"method":[88],"is":[89,110,119,132,144],"developed":[90],"for":[91],"transferring":[92],"information":[93,109],"gathered":[94],"world":[98],"back":[99],"agent":[103],"new":[108,142],"re-evaluate":[113],"whether":[114],"original":[116],"simulated":[117],"still":[120],"given":[122],"updated":[124],"knowledge":[125],"real-world.":[128],"This":[129],"reverse":[130],"transfer":[131],"critical":[133],"demonstrated":[145],"on":[146],"robotic":[148],"car":[149],"perform":[152],"controlled":[153],"drifting":[154],"maneuvers.":[155],"video":[157],"car's":[160],"performance":[161],"can":[162],"be":[163],"found":[164],"at":[165],"https:":[166],"//youtu.be/opsmd5yuBF0.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}