{"id":"https://openalex.org/W2981233685","doi":"https://doi.org/10.1007/s10994-021-06116-1","title":"Reinforcement learning for robotic manipulation using simulated locomotion demonstrations","display_name":"Reinforcement learning for robotic manipulation using simulated locomotion demonstrations","publication_year":2021,"publication_date":"2021-11-24","ids":{"openalex":"https://openalex.org/W2981233685","doi":"https://doi.org/10.1007/s10994-021-06116-1","mag":"2981233685"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-021-06116-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06116-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06116-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06116-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075243103","display_name":"Ozsel Kilinc","orcid":"https://orcid.org/0000-0002-5269-2382"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ozsel Kilinc","raw_affiliation_strings":["WMG, University of Warwick, Coventry, UK","University of Warwick"],"raw_orcid":"https://orcid.org/0000-0002-5269-2382","affiliations":[{"raw_affiliation_string":"WMG, University of Warwick, Coventry, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010581004","display_name":"Giovanni Montana","orcid":"https://orcid.org/0000-0003-3942-3900"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giovanni Montana","raw_affiliation_strings":["WMG, University of Warwick, Coventry, UK","University of Warwick"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WMG, University of Warwick, Coventry, UK","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.9795,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79766129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"111","issue":"2","first_page":"465","last_page":"486"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8342604637145996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7561613917350769},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7555397748947144},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6897414922714233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6386332511901855},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6192839741706848},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5220317840576172},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43211138248443604},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.42508214712142944},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4245035648345947},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4102935791015625},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3641093671321869},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10592982172966003}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8342604637145996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561613917350769},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7555397748947144},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6897414922714233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6386332511901855},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6192839741706848},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5220317840576172},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43211138248443604},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.42508214712142944},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4245035648345947},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4102935791015625},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3641093671321869},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10592982172966003},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10994-021-06116-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06116-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06116-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:wrap.warwick.ac.uk:161382","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:1910.07294","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.07294","pdf_url":"https://arxiv.org/pdf/1910.07294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},{"id":"mag:2981233685","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.07294","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.1910.07294","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.07294","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/s10994-021-06116-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06116-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06116-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4160449099","display_name":null,"funder_award_id":"EP/V024868/1","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981233685.pdf","grobid_xml":"https://content.openalex.org/works/W2981233685.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1557517019","https://openalex.org/W1672285122","https://openalex.org/W1771410628","https://openalex.org/W1863227302","https://openalex.org/W1931877416","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2083561185","https://openalex.org/W2115519999","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2167224731","https://openalex.org/W2167340365","https://openalex.org/W2171054284","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2287850282","https://openalex.org/W2290104316","https://openalex.org/W2342840547","https://openalex.org/W2402734324","https://openalex.org/W2417786368","https://openalex.org/W2544683879","https://openalex.org/W2559767995","https://openalex.org/W2575705757","https://openalex.org/W2603088459","https://openalex.org/W2610395436","https://openalex.org/W2616430965","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2781726626","https://openalex.org/W2788781499","https://openalex.org/W2788862220","https://openalex.org/W2789008106","https://openalex.org/W2805762288","https://openalex.org/W2885163910","https://openalex.org/W2885550588","https://openalex.org/W2889347284","https://openalex.org/W2895453875","https://openalex.org/W2896313218","https://openalex.org/W2899205164","https://openalex.org/W2911383979","https://openalex.org/W2914931737","https://openalex.org/W2939047085","https://openalex.org/W2944911388","https://openalex.org/W2962779270","https://openalex.org/W2962937519","https://openalex.org/W2962957031","https://openalex.org/W2963094133","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963280855","https://openalex.org/W2963293881","https://openalex.org/W2963363446","https://openalex.org/W2963376229","https://openalex.org/W2963504959","https://openalex.org/W2963523627","https://openalex.org/W2963577640","https://openalex.org/W2963590100","https://openalex.org/W2963639957","https://openalex.org/W2963864421","https://openalex.org/W2963960193","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964118020","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2964342357","https://openalex.org/W2968340082","https://openalex.org/W2990747716","https://openalex.org/W3127352841","https://openalex.org/W4206567137","https://openalex.org/W6616173779","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6684205842","https://openalex.org/W6696273291","https://openalex.org/W6718092244","https://openalex.org/W6735944222","https://openalex.org/W6740801417","https://openalex.org/W6748314335","https://openalex.org/W6753060773"],"related_works":["https://openalex.org/W3005595008","https://openalex.org/W3171592859","https://openalex.org/W3111393852","https://openalex.org/W3131590559","https://openalex.org/W2968340082","https://openalex.org/W3209823187","https://openalex.org/W2523013761","https://openalex.org/W3046125856","https://openalex.org/W2953326790","https://openalex.org/W3206093119","https://openalex.org/W3086628038","https://openalex.org/W3004815632","https://openalex.org/W2805810890","https://openalex.org/W3206200647","https://openalex.org/W3205641566","https://openalex.org/W2976087063","https://openalex.org/W3133085002","https://openalex.org/W2589275886","https://openalex.org/W2950631193","https://openalex.org/W3098105401"],"abstract_inverted_index":{"Abstract":[0],"Mastering":[1],"robotic":[2,103],"manipulation":[3,104,181],"skills":[4],"through":[5],"reinforcement":[6],"learning":[7,59,203],"(RL)":[8],"typically":[9],"requires":[10],"the":[11,30,34,69,115,118,123,179],"design":[12],"of":[13,117,192],"shaped":[14],"reward":[15],"functions.":[16],"Recent":[17,55],"developments":[18],"in":[19,52],"this":[20,53,84,140],"area":[21],"have":[22,63],"demonstrated":[23],"that":[24,93,101],"using":[25,154],"sparse":[26,61],"rewards,":[27,167],"i.e.":[28,122],"rewarding":[29],"agent":[31],"only":[32],"when":[33],"task":[35,105,113],"has":[36,186],"been":[37,187],"successfully":[38],"completed,":[39],"can":[40,73,196],"lead":[41],"to":[42,58,81,128,138,164,177,206],"better":[43],"policies.":[44],"However,":[45],"state-action":[46],"space":[47],"exploration":[48],"is":[49,151,161],"more":[50],"difficult":[51],"case.":[54],"RL":[56],"approaches":[57],"with":[60],"rewards":[62,172],"leveraged":[64],"high-quality":[65],"human":[66,97],"demonstrations":[67],"for":[68,213],"task,":[70],"but":[71],"these":[72],"be":[74,107],"costly,":[75],"time":[76],"consuming":[77],"or":[78],"even":[79],"impossible":[80],"obtain.":[82],"In":[83,136],"paper,":[85],"we":[86,142],"propose":[87],"a":[88,111,130,144,155],"novel":[89],"and":[90,195,201,218],"effective":[91],"approach":[92,185],"does":[94],"not":[95],"require":[96],"demonstrations.":[98],"We":[99],"observe":[100],"every":[102],"could":[106,125],"seen":[108],"as":[109],"involving":[110],"locomotion":[112,149,170],"from":[114],"perspective":[116],"object":[119,124,148,220],"being":[120],"manipulated,":[121],"learn":[126,178],"how":[127],"reach":[129],"target":[131],"state":[132],"on":[133,189],"its":[134],"own.":[135],"order":[137],"exploit":[139],"idea,":[141],"introduce":[143],"framework":[145],"whereby":[146],"an":[147],"policy":[150,160],"initially":[152],"obtained":[153],"realistic":[156],"physics":[157],"simulator.":[158],"This":[159],"then":[162],"used":[163],"generate":[165],"auxiliary":[166],"called":[168],"simulated":[169],"demonstration":[171],"(SLDRs),":[173],"which":[174],"enable":[175],"us":[176],"robot":[180],"policy.":[182],"The":[183],"proposed":[184],"evaluated":[188],"13":[190],"tasks":[191,214],"increasing":[193],"complexity,":[194],"achieve":[197],"higher":[198],"success":[199],"rate":[200],"faster":[202],"rates":[204],"compared":[205],"alternative":[207],"algorithms.":[208],"SLDRs":[209],"are":[210],"especially":[211],"beneficial":[212],"like":[215],"multi-object":[216],"stacking":[217],"non-rigid":[219],"manipulation.":[221]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}