{"id":"https://openalex.org/W2045330530","doi":"https://doi.org/10.1109/iros.2013.6696585","title":"Skills transfer across dissimilar robots by learning context-dependent rewards","display_name":"Skills transfer across dissimilar robots by learning context-dependent rewards","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2045330530","doi":"https://doi.org/10.1109/iros.2013.6696585","mag":"2045330530"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5044760115","display_name":"Milad Malekzadeh","orcid":"https://orcid.org/0000-0003-2275-0497"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Milad S. Malekzadeh","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044420843","display_name":"Danilo Bruno","orcid":null},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Bruno","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048780399","display_name":"Sylvain Calinon","orcid":"https://orcid.org/0000-0002-9036-6799"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sylvain Calinon","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060656142","display_name":"Thrishantha Nanayakkara","orcid":"https://orcid.org/0000-0002-1882-1232"},"institutions":[{"id":"https://openalex.org/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]},{"id":"https://openalex.org/I4210160447","display_name":"Universidad de Londres","ror":"https://ror.org/054v4yq51","country_code":"MX","type":"education","lineage":["https://openalex.org/I4210160447"]}],"countries":["GB","MX"],"is_corresponding":false,"raw_author_name":"Thrishantha Nanayakkara","raw_affiliation_strings":["Division of Engineering, University of London, Strand, London","Div. of Eng., Univ. of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Division of Engineering, University of London, Strand, London","institution_ids":["https://openalex.org/I124357947","https://openalex.org/I4210160447"]},{"raw_affiliation_string":"Div. of Eng., Univ. of London, London, UK","institution_ids":["https://openalex.org/I124357947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044243940","display_name":"Darwin G. Caldwell","orcid":"https://orcid.org/0000-0002-6233-9961"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Darwin G. Caldwell","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Dept. of Adv. Robot., Ist. Italiano di Tecnol. (IIT), Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044760115"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":6.1051,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96057777,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"1746","last_page":"1751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9868999719619751,"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"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9634000062942505,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7086760401725769},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6551724672317505},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6128119230270386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6078536510467529},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5651991367340088},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.563823401927948},{"id":"https://openalex.org/keywords/kinesthetic-learning","display_name":"Kinesthetic learning","score":0.5551505088806152},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5360347032546997},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5272223949432373},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44898751378059387},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4236282408237457},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37814217805862427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10253897309303284},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08947959542274475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7086760401725769},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6551724672317505},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6128119230270386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6078536510467529},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5651991367340088},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.563823401927948},{"id":"https://openalex.org/C55457006","wikidata":"https://www.wikidata.org/wiki/Q3647098","display_name":"Kinesthetic learning","level":2,"score":0.5551505088806152},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5360347032546997},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5272223949432373},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44898751378059387},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4236282408237457},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37814217805862427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10253897309303284},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08947959542274475},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","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":5,"locations":[{"id":"doi:10.1109/iros.2013.6696585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.433.7601","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.433.7601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.calinon.ch/papers/Malekzadeh-IROS2013.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.5158","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.5158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://thrish.org/wp/wp-content/uploads/2014/08/Malekzadeh-IROS2013.pdf","raw_type":"text"},{"id":"pmh:oai:iris.unige.it:11567/799014","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/799014","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/ffa19a9b-4afa-415d-9c3f-4a668c43de2c","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/ffa19a9b-4afa-415d-9c3f-4a668c43de2c","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Malekzadeh , M S , Bruno , D , Calinon , S , Nanayakkara , T & G. Caldwell , D 2013 , Skills Transfer across Dissimilar Robots by Learning Context-Dependent Rewards . in 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . N/A edn , vol. N/A , N/A , pp. 1746-1751 . https://doi.org/10.1109/IROS.2013.6696585","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W123233698","https://openalex.org/W1533729189","https://openalex.org/W1591675293","https://openalex.org/W1972336342","https://openalex.org/W1973102501","https://openalex.org/W2012612381","https://openalex.org/W2038674173","https://openalex.org/W2056536535","https://openalex.org/W2071841410","https://openalex.org/W2080039641","https://openalex.org/W2098524868","https://openalex.org/W2120772693","https://openalex.org/W2124172617","https://openalex.org/W2126105931","https://openalex.org/W2128677288","https://openalex.org/W2141481921","https://openalex.org/W2142916680","https://openalex.org/W2156163138","https://openalex.org/W2536057734","https://openalex.org/W4285719527","https://openalex.org/W6631933356","https://openalex.org/W6635261211","https://openalex.org/W6674872077","https://openalex.org/W6729118241"],"related_works":["https://openalex.org/W3111440524","https://openalex.org/W2558272010","https://openalex.org/W2068552404","https://openalex.org/W4392899229","https://openalex.org/W2921166921","https://openalex.org/W4385174651","https://openalex.org/W3162087156","https://openalex.org/W1597792207","https://openalex.org/W3213722473","https://openalex.org/W2110944602"],"abstract_inverted_index":{"Robot":[0],"programming":[1],"by":[2],"demonstration":[3],"encompasses":[4],"a":[5,46,137,148,163,185,196],"wide":[6],"range":[7],"of":[8,14,23,37,48,58,63,87,114,174,188],"learning":[9,71],"strategies,":[10],"from":[11,45,195],"simple":[12],"mimicking":[13],"the":[15,19,24,35,39,43,59,64,75,85,88,96,101,115,122,134,144,154],"demonstrator's":[16],"actions":[17],"to":[18,132,146,161,169],"higher":[20],"level":[21,150],"extraction":[22],"underlying":[25],"intent.":[26],"By":[27,90],"focusing":[28],"on":[29,92,141],"this":[30,54],"last":[31],"form,":[32],"we":[33],"study":[34],"problem":[36,65],"extracting":[38],"reward":[40,50,81,104,127],"function":[41,82],"explaining":[42,121],"demonstrations":[44,194],"set":[47],"candidate":[49,103],"functions,":[51],"and":[52,108],"using":[53,192],"information":[55],"for":[56,120],"self-refinement":[57,138],"skill.":[60],"This":[61],"definition":[62],"has":[66],"links":[67],"with":[68,136,184],"inverse":[69],"reinforcement":[70],"problems":[72],"in":[73,109,165,182],"which":[74,110],"robot":[76,190],"autonomously":[77],"extracts":[78],"an":[79],"optimal":[80],"that":[83,151],"defines":[84],"goal":[86],"task.":[89],"relying":[91],"Gaussian":[93],"mixture":[94],"models,":[95],"proposed":[97,178],"approach":[98,139,157,179],"learns":[99],"how":[100],"different":[102,166,175],"functions":[105],"are":[106,118],"combined,":[107],"contexts":[111],"or":[112,168],"phases":[113],"task":[116],"they":[117],"relevant":[119],"user's":[123],"demonstrations.":[124,155],"The":[125,156,177],"extracted":[126],"profile":[128],"is":[129,180],"then":[130],"exploited":[131],"improve":[133],"skill":[135,149,164],"based":[140],"expectation-maximization,":[142],"allowing":[143],"imitator":[145],"reach":[147],"goes":[152],"beyond":[153],"can":[158],"be":[159],"used":[160],"reproduce":[162],"ways":[167],"transfer":[170],"tasks":[171],"across":[172],"robots":[173],"structures.":[176],"tested":[181],"simulation":[183],"new":[186],"type":[187],"continuum":[189],"(STIFF-FLOP),":[191],"kinesthetic":[193],"Barrett":[197],"WAM":[198],"manipulator.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}