{"id":"https://openalex.org/W2795561664","doi":"https://doi.org/10.1109/icra.2018.8461203","title":"Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learning","display_name":"Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2795561664","doi":"https://doi.org/10.1109/icra.2018.8461203","mag":"2795561664"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","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/A5006960979","display_name":"Linhai Xie","orcid":"https://orcid.org/0000-0001-8593-2277"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Linhai Xie","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350760","display_name":"Sen Wang","orcid":"https://orcid.org/0000-0003-1537-8834"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sen Wang","raw_affiliation_strings":["School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I32062511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047782253","display_name":"Stefano Rosa","orcid":"https://orcid.org/0000-0001-6458-6344"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefano Rosa","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060183988","display_name":"Andrew Markham","orcid":"https://orcid.org/0000-0001-5716-3941"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Markham","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010637110","display_name":"Niki Trigoni","orcid":"https://orcid.org/0000-0001-6236-9645"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Niki Trigoni","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006960979"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":7.7753,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.97803516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6276","last_page":"6283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9952999949455261,"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":0.832061767578125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460410594940186},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6668801307678223},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6157708764076233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5579083561897278},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5503414273262024},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5138568878173828},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5041810274124146},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5028297305107117},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.4729715883731842},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42840248346328735},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.31802600622177124},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.274760901927948},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14520472288131714}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.832061767578125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460410594940186},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6668801307678223},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6157708764076233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579083561897278},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5503414273262024},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5138568878173828},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5041810274124146},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5028297305107117},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.4729715883731842},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42840248346328735},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.31802600622177124},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.274760901927948},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14520472288131714},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra.2018.8461203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:f8fad305-6a85-4512-b8b5-4eb39bd15d26","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:f8fad305-6a85-4512-b8b5-4eb39bd15d26","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"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 item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2483205037","display_name":null,"funder_award_id":"EP/M019918/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1543703002","https://openalex.org/W1923344279","https://openalex.org/W2095784398","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2201581102","https://openalex.org/W2296673577","https://openalex.org/W2524241275","https://openalex.org/W2598706937","https://openalex.org/W2601322194","https://openalex.org/W2610859226","https://openalex.org/W2732319713","https://openalex.org/W2741122588","https://openalex.org/W2950471160","https://openalex.org/W2951799221","https://openalex.org/W2952348863","https://openalex.org/W2962736495","https://openalex.org/W2962957005","https://openalex.org/W2963019567","https://openalex.org/W2963428623","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964118262","https://openalex.org/W3106440972","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6697071109","https://openalex.org/W6704665273","https://openalex.org/W6727548329","https://openalex.org/W6730329805","https://openalex.org/W6734744077"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2782776446","https://openalex.org/W3043170174","https://openalex.org/W2155948905","https://openalex.org/W2357323510"],"abstract_inverted_index":{"Deep":[0,172],"Reinforcement":[1,61],"Learning":[2],"(DRL)":[3],"has":[4],"been":[5],"applied":[6],"successfully":[7],"to":[8,30,52,78,102,129,160],"many":[9],"robotic":[10],"applications.":[11],"However,":[12],"the":[13,95,100,118,138,161,164,179],"large":[14],"number":[15],"of":[16,26,82,114,163],"trials":[17],"needed":[18],"for":[19,44,84],"training":[20,32,81],"is":[21,71,93,157],"a":[22,57,64,68,110,170],"key":[23],"issue.":[24],"Most":[25],"existing":[27],"techniques":[28],"developed":[29],"improve":[31],"efficiency":[33],"(e.g.":[34,67],"imitation)":[35],"target":[36],"on":[37],"general":[38],"tasks":[39],"rather":[40],"than":[41],"being":[42],"tailored":[43],"robot":[45,101],"applications,":[46],"which":[47],"have":[48],"their":[49],"specific":[50],"context":[51],"benefit":[53],"from.":[54],"We":[55,145,177],"propose":[56],"novel":[58],"framework,":[59],"Assisted":[60],"Learning,":[62],"where":[63],"classical":[65],"controller":[66,140],"PID":[69],"controller)":[70],"used":[72],"as":[73],"an":[74],"alternative,":[75],"switchable":[76],"policy":[77],"speed":[79],"up":[80],"DRL":[83,165],"local":[85],"planning":[86],"and":[87,167,184],"navigation":[88],"problems.":[89],"The":[90],"core":[91],"idea":[92],"that":[94,147],"simple":[96,139],"control":[97],"law":[98],"allows":[99],"rapidly":[103],"learn":[104],"sensible":[105],"primitives,":[106],"like":[107,134],"driving":[108],"in":[109,181],"straight":[111],"line,":[112],"instead":[113],"random":[115],"exploration.":[116],"As":[117],"actor":[119],"network":[120,166],"becomes":[121],"more":[122,131],"advanced,":[123],"it":[124,155],"can":[125,141],"then":[126],"take":[127],"over":[128],"perform":[130],"complex":[132],"actions,":[133],"obstacle":[135],"avoidance.":[136],"Eventually,":[137],"be":[142],"discarded":[143],"entirely.":[144],"show":[146],"not":[148],"only":[149],"does":[150],"this":[151],"technique":[152],"train":[153],"faster,":[154],"also":[156],"less":[158],"sensitive":[159],"structure":[162],"consistently":[168],"outperforms":[169],"standard":[171],"Deterministic":[173],"Policy":[174],"Gradient":[175],"network.":[176],"demonstrate":[178],"results":[180],"both":[182],"simulation":[183],"real-world":[185],"experiments.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}