{"id":"https://openalex.org/W2093192040","doi":"https://doi.org/10.1109/iros.2013.6696817","title":"Transfer in inverse reinforcement learning for multiple strategies","display_name":"Transfer in inverse reinforcement learning for multiple strategies","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2093192040","doi":"https://doi.org/10.1109/iros.2013.6696817","mag":"2093192040"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696817","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":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/187590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088063475","display_name":"Ajay Kumar Tanwani","orcid":"https://orcid.org/0000-0002-6365-8315"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]}],"countries":["CH","FR"],"is_corresponding":true,"raw_author_name":"Ajay Kumar Tanwani","raw_affiliation_strings":["Learning Algorithms and Systems Laboratory (LASA) Ecole Polytechnique Federale de Lausanne, Switzerland","Learning Algorithms & Syst. Lab. (LASA), Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Learning Algorithms and Systems Laboratory (LASA) Ecole Polytechnique Federale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Learning Algorithms & Syst. Lab. (LASA), Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I29607241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090592452","display_name":"Aude Billard","orcid":"https://orcid.org/0000-0002-7076-8010"},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH","FR"],"is_corresponding":false,"raw_author_name":"Aude Billard","raw_affiliation_strings":["Learning Algorithms and Systems Laboratory (LASA) Ecole Polytechnique Federale de Lausanne, Switzerland","Learning Algorithms & Syst. Lab. (LASA), Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Learning Algorithms and Systems Laboratory (LASA) Ecole Polytechnique Federale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Learning Algorithms & Syst. Lab. (LASA), Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I29607241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088063475"],"corresponding_institution_ids":["https://openalex.org/I29607241","https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":1.9775,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88873083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"3244","last_page":"3250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.995199978351593,"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":0.9932000041007996,"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/set","display_name":"Set (abstract data type)","score":0.7345477938652039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717918872833252},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6860427260398865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6148927211761475},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6136614680290222},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5788971781730652},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5735832452774048},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5219130516052246},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42731526494026184},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07886826992034912}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7345477938652039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717918872833252},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6860427260398865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6148927211761475},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6136614680290222},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5788971781730652},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5735832452774048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5219130516052246},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42731526494026184},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07886826992034912},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/iros.2013.6696817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696817","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:10.1.1.363.3743","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.3743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/187590/files/Tanwani_iros13.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.4855","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.4855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lasa.epfl.ch/publications/uploadedFiles/Tanwani_iros13.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:187590","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/187590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:187590","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/record/187590/files/Tanwani_iros13_HD.wmv","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},{"id":"pmh:oai:infoscience.tind.io:199259","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/199259","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/199259","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:187590","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/187590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1567876833","https://openalex.org/W1591675293","https://openalex.org/W1684361744","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2097381042","https://openalex.org/W2098774185","https://openalex.org/W2102847492","https://openalex.org/W2113023245","https://openalex.org/W2119567691","https://openalex.org/W2119914747","https://openalex.org/W2132057084","https://openalex.org/W2169498096","https://openalex.org/W2181849516","https://openalex.org/W2334782222","https://openalex.org/W2950989964","https://openalex.org/W4211008118","https://openalex.org/W6635261211","https://openalex.org/W6674600207","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677978604","https://openalex.org/W6685962732"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"We":[0,41,138],"consider":[1],"the":[2,27,30,52,84,120,125,148,167,171],"problem":[3],"of":[4,9,18,24,38,73,76,92,110,127,151,170],"incrementally":[5],"learning":[6,111],"different":[7,61,162],"strategies":[8,86,169],"performing":[10,39],"a":[11,22,60,70,74,89,143],"complex":[12],"sequential":[13],"task":[14,28,146],"from":[15,96,106,112,124],"multiple":[16],"demonstrations":[17],"an":[19],"expert":[20,33,85,103],"or":[21],"set":[23,75,91,126],"experts.":[25],"While":[26],"is":[29,49,57,67],"same,":[31],"each":[32,55],"differs":[34],"in":[35,117,164],"his/her":[36],"way":[37],"it.":[40],"assume":[42],"that":[43,54],"this":[44,107,118],"variety":[45],"across":[46],"experts'":[47],"demonstration":[48],"due":[50],"to":[51,130,158],"fact":[53],"expert/strategy":[56],"driven":[58],"by":[59,87],"reward":[62,65],"function,":[63],"where":[64,147],"function":[66],"expressed":[68],"as":[69],"linear":[71],"combination":[72],"known":[77],"features.":[78],"Consequently,":[79],"we":[80],"can":[81,99],"learn":[82],"all":[83],"forming":[88],"convex":[90],"optimal":[93,115,136],"deterministic":[94],"policies,":[95],"which":[97],"one":[98],"match":[100],"any":[101],"unseen":[102],"strategy":[104],"drawn":[105],"set.":[108],"Instead":[109],"scratch":[113],"every":[114],"policy":[116],"set,":[119],"learner":[121],"transfers":[122],"knowledge":[123],"learned":[128],"policies":[129],"bootstrap":[131],"its":[132],"search":[133],"for":[134],"new":[135],"policy.":[137],"demonstrate":[139],"our":[140],"approach":[141],"on":[142,161],"simulated":[144],"mini-golf":[145],"7":[149],"degrees":[150],"freedom":[152],"Barrett":[153],"WAM":[154],"robot":[155],"arm":[156],"learns":[157],"sequentially":[159],"putt":[160],"holes":[163],"accordance":[165],"with":[166],"playing":[168],"expert.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
