{"id":"https://openalex.org/W3196158767","doi":"https://doi.org/10.1109/icdl49984.2021.9515637","title":"Inverse reinforcement learning for dexterous hand manipulation","display_name":"Inverse reinforcement learning for dexterous hand manipulation","publication_year":2021,"publication_date":"2021-08-20","ids":{"openalex":"https://openalex.org/W3196158767","doi":"https://doi.org/10.1109/icdl49984.2021.9515637","mag":"3196158767"},"language":"en","primary_location":{"id":"doi:10.1109/icdl49984.2021.9515637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl49984.2021.9515637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mediatum.ub.tum.de/1632205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059129926","display_name":"J\u0119drzej Orbik","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jedrzej Orbik","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051585666","display_name":"Alejandro Agostini","orcid":"https://orcid.org/0000-0002-4894-8752"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT","DE"],"is_corresponding":false,"raw_author_name":"Alejandro Agostini","raw_affiliation_strings":["Technical University of Munich, Munich, Germany","University of Innsbruck, Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088081800","display_name":"Dongheui Lee","orcid":"https://orcid.org/0000-0003-1897-7664"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dongheui Lee","raw_affiliation_strings":["German Aerospace Center (DLR), Institute of Robotics and Mechatronics, Wessling, Germany","Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"German Aerospace Center (DLR), Institute of Robotics and Mechatronics, Wessling, Germany","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059129926"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.5599,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73385149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9872999787330627,"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":0.9872999787330627,"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":0.9812999963760376,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9771000146865845,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7322208285331726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.701768159866333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6029936671257019},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5398465991020203},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4360715448856354},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43406766653060913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4200300872325897},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41649115085601807},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41533762216567993},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1490693986415863}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7322208285331726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701768159866333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6029936671257019},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5398465991020203},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4360715448856354},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43406766653060913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4200300872325897},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41649115085601807},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41533762216567993},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1490693986415863},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdl49984.2021.9515637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl49984.2021.9515637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:elib.dlr.de:147178","is_oa":false,"landing_page_url":"https://elib.dlr.de/147178/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzbeitrag"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1632205","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1632205","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1632205","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1632205","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1564897360","https://openalex.org/W1710476689","https://openalex.org/W1945616565","https://openalex.org/W2121863487","https://openalex.org/W2158782408","https://openalex.org/W2312161484","https://openalex.org/W2460937040","https://openalex.org/W2509374375","https://openalex.org/W2552241273","https://openalex.org/W2566467060","https://openalex.org/W2610395436","https://openalex.org/W2741933435","https://openalex.org/W2791846357","https://openalex.org/W2945924974","https://openalex.org/W2963170432","https://openalex.org/W2963207607","https://openalex.org/W2963211300","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2963508354","https://openalex.org/W2964253222","https://openalex.org/W2968771440","https://openalex.org/W2970317235","https://openalex.org/W2981030070","https://openalex.org/W2990747716","https://openalex.org/W2996343955","https://openalex.org/W2996564870","https://openalex.org/W2998835636","https://openalex.org/W3103251932","https://openalex.org/W4288263167","https://openalex.org/W4288363925","https://openalex.org/W4293864724","https://openalex.org/W4297795595","https://openalex.org/W4298289240","https://openalex.org/W4300511536","https://openalex.org/W6627932998","https://openalex.org/W6637568146","https://openalex.org/W6640425456","https://openalex.org/W6698662012","https://openalex.org/W6718092244","https://openalex.org/W6719080892","https://openalex.org/W6729653997","https://openalex.org/W6731259203","https://openalex.org/W6739868092","https://openalex.org/W6742759968","https://openalex.org/W6744563498","https://openalex.org/W6745347688","https://openalex.org/W6761100157","https://openalex.org/W6767044207","https://openalex.org/W6770858630","https://openalex.org/W6771809012"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2591697403","https://openalex.org/W3196817267"],"abstract_inverted_index":{"The":[0,23],"success":[1],"of":[2,38,75,99,106,149],"deep":[3],"reinforcement":[4,60],"learning":[5,61,145],"approaches":[6,88],"to":[7,18,27,34,64,96,115,135],"learn":[8,66],"dexterous":[9,39,107,152],"manipulation":[10,108,153],"skills":[11],"strongly":[12,90],"hinges":[13],"on":[14],"the":[15,29,35,41,67,82,97,102],"rewards":[16,84],"assigned":[17],"actions":[19,94],"during":[20,122],"task":[21],"execution.":[22],"usual":[24],"approach":[25,63,143],"is":[26],"handcraft":[28],"reward":[30,42,68,117,133],"function":[31,69],"but":[32],"due":[33,95,114],"high":[36],"complexity":[37],"manipulations":[40],"definition":[43],"demands":[44],"large":[45],"engineering":[46],"effort":[47],"for":[48,128,151],"each":[49],"particular":[50],"task.":[51],"To":[52],"avoid":[53],"this":[54,137,142],"burden,":[55],"we":[56],"use":[57,125],"an":[58],"inverse":[59],"(IRL)":[62],"automatically":[65],"using":[70,85],"samples":[71,100],"obtained":[72],"from":[73],"demonstrations":[74],"desired":[76],"behaviours.":[77],"We":[78,124,139],"have":[79],"identified":[80],"that":[81,141],"learned":[83],"existing":[86],"IRL":[87,150],"are":[89],"biased":[91],"towards":[92],"demonstrated":[93],"scarcity":[98],"in":[101,119],"vast":[103],"state-action":[104],"space":[105],"applications.":[109],"This":[110],"significantly":[111],"hinders":[112],"performance":[113],"unreliable":[116],"estimations":[118],"regions":[120],"unexplored":[121],"demonstration.":[123],"statistical":[126],"tools":[127],"random":[129],"sample":[130],"generation":[131],"and":[132,147],"normalization":[134],"reduce":[136],"bias.":[138],"show":[140],"improves":[144],"stability":[146],"transferability":[148],"tasks.":[154],"Project":[155],"page:":[156],"https://sites.google.con":[157],"view/irl-for-dexterous-hand":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
