{"id":"https://openalex.org/W2097364276","doi":"https://doi.org/10.1109/iros.2007.4399449","title":"Using reinforcement learning to adapt an imitation task","display_name":"Using reinforcement learning to adapt an imitation task","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2097364276","doi":"https://doi.org/10.1109/iros.2007.4399449","mag":"2097364276"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2007.4399449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 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/114048","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075553496","display_name":"F. Guenter","orcid":null},"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"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Florent Guenter","raw_affiliation_strings":["Learning Algorithms and Systems Laboratory, School of Engineering, Ecole Polytechnique Federale de Lausanne, Switzerland","Ecole Polytech. Fed. de Lausanne, Lausanne"],"affiliations":[{"raw_affiliation_string":"Learning Algorithms and Systems Laboratory, School of Engineering, Ecole Polytechnique Federale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Ecole Polytech. Fed. de Lausanne, Lausanne","institution_ids":["https://openalex.org/I5124864"]}]},{"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/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"],"is_corresponding":false,"raw_author_name":"Aude G. Billard","raw_affiliation_strings":["Learning Algorithms and Systems Laboratory, School of Engineering, Ecole Polytechnique Federale de Lausanne, Switzerland","Ecole Polytech. Fed. de Lausanne, Lausanne"],"affiliations":[{"raw_affiliation_string":"Learning Algorithms and Systems Laboratory, School of Engineering, Ecole Polytechnique Federale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Ecole Polytech. Fed. de Lausanne, Lausanne","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075553496"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":2.4148,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90196426,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"1022","last_page":"1027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9962000250816345,"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/task","display_name":"Task (project management)","score":0.8042818307876587},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7890262603759766},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7875438928604126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7570557594299316},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6758126616477966},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.6461750268936157},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6139498949050903},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5714625120162964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5602942109107971},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4148951470851898},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3190028667449951},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13780981302261353}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.8042818307876587},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7890262603759766},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7875438928604126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570557594299316},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6758126616477966},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.6461750268936157},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6139498949050903},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5714625120162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5602942109107971},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4148951470851898},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3190028667449951},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13780981302261353},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros.2007.4399449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.216.2558","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.216.2558","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/IROS07.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:114048","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/114048","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"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:114048","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/114048","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W41808307","https://openalex.org/W1483198858","https://openalex.org/W1507222174","https://openalex.org/W1531166221","https://openalex.org/W1592847719","https://openalex.org/W1594783240","https://openalex.org/W1952489873","https://openalex.org/W1970789124","https://openalex.org/W2037461669","https://openalex.org/W2063645887","https://openalex.org/W2103447784","https://openalex.org/W2113501460","https://openalex.org/W2114537044","https://openalex.org/W2116039916","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2128221272","https://openalex.org/W2128677288","https://openalex.org/W2132351269","https://openalex.org/W2133341504","https://openalex.org/W2152931627","https://openalex.org/W2153947321","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2167647761","https://openalex.org/W2171493306","https://openalex.org/W4214717370","https://openalex.org/W6635508374","https://openalex.org/W6640954454","https://openalex.org/W6677049199","https://openalex.org/W6679317373","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W7075606714"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2117552637"],"abstract_inverted_index":{"The":[0,47],"goal":[1],"of":[2,16,38],"developing":[3],"algorithms":[4],"for":[5],"programming":[6,17],"robots":[7,18],"by":[8,23,88],"demonstration":[9],"is":[10],"to":[11,31,53,67,83],"create":[12],"an":[13],"easy":[14],"way":[15],"that":[19,79,97],"can":[20],"be":[21,51],"accomplished":[22],"everyone.":[24],"When":[25],"a":[26,29,32,69,77,81],"demonstrator":[27],"teaches":[28],"task":[30,56],"robot,":[33],"he/she":[34],"shows":[35],"some":[36],"ways":[37],"fulfilling":[39],"the":[40,45,55,90,94],"task,":[41],"but":[42],"not":[43],"all":[44],"possibilities.":[46],"robot":[48,82],"must":[49],"then":[50],"able":[52],"reproduce":[54],"even":[57],"when":[58],"unexpected":[59],"perturbations":[60],"occur.":[61],"In":[62,72],"this":[63,73],"case,":[64],"it":[65],"has":[66],"learn":[68],"new":[70],"solution.":[71],"paper,":[74],"we":[75],"describe":[76],"system":[78],"allows":[80],"re-learn":[84],"constrained":[85],"reaching":[86],"tasks":[87],"combining":[89],"knowledge":[91],"acquired":[92,98],"during":[93],"demonstration,":[95],"with":[96],"though":[99],"reinforcement":[100],"learning.":[101]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
