{"id":"https://openalex.org/W1968251327","doi":"https://doi.org/10.1109/adprl.2009.4927549","title":"Using reward-weighted imitation for robot Reinforcement Learning","display_name":"Using reward-weighted imitation for robot Reinforcement Learning","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W1968251327","doi":"https://doi.org/10.1109/adprl.2009.4927549","mag":"1968251327"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]},{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"funder","lineage":["https://openalex.org/I149899117"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Department of Empirical Inference and Machine Learning, Max-Planck Institute of Biological Cybernetics, Tubingen, Germany","Department of Empirical Inference and Machine Learning, Max Planck Institute for Biological Cybernetics, Spemannstr. 38, 72076 T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Empirical Inference and Machine Learning, Max-Planck Institute of Biological Cybernetics, Tubingen, Germany","institution_ids":["https://openalex.org/I4210112925"]},{"raw_affiliation_string":"Department of Empirical Inference and Machine Learning, Max Planck Institute for Biological Cybernetics, Spemannstr. 38, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"funder","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Kober","raw_affiliation_strings":["Department of Empirical Inference and Machine Learning, Max-Planck Institute of Biological Cybernetics, Tubingen, Germany","Department of Empirical Inference and Machine Learning, Max Planck Institute for Biological Cybernetics, Spemannstr. 38, 72076 T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Empirical Inference and Machine Learning, Max-Planck Institute of Biological Cybernetics, Tubingen, Germany","institution_ids":["https://openalex.org/I4210112925"]},{"raw_affiliation_string":"Department of Empirical Inference and Machine Learning, Max Planck Institute for Biological Cybernetics, Spemannstr. 38, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I149899117"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071367253"],"corresponding_institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210112925"],"apc_list":null,"apc_paid":null,"fwci":1.3549,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83949871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"165","issue":null,"first_page":"226","last_page":"232"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9940000176429749,"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":0.895054817199707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6944459676742554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6656251549720764},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6562190651893616},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6372195482254028},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5774962902069092},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5571112632751465},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5395019054412842},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4578404128551483},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45409271121025085},{"id":"https://openalex.org/keywords/motor-learning","display_name":"Motor learning","score":0.4287243187427521},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4151949882507324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4074733853340149},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.23939362168312073},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12748438119888306},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11514469981193542},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09361281991004944}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.895054817199707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6944459676742554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656251549720764},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6562190651893616},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6372195482254028},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5774962902069092},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5571112632751465},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5395019054412842},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4578404128551483},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45409271121025085},{"id":"https://openalex.org/C107690735","wikidata":"https://www.wikidata.org/wiki/Q852461","display_name":"Motor learning","level":2,"score":0.4287243187427521},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4151949882507324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4074733853340149},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.23939362168312073},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12748438119888306},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11514469981193542},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09361281991004944},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/adprl.2009.4927549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:edoc.mpg.de:461809","is_oa":false,"landing_page_url":"http://edoc.mpg.de/461809","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"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":"Proceedings of the 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL 2009), 226-232 (2009)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1789382","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-C505-6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W990093006","https://openalex.org/W1516801383","https://openalex.org/W1564755532","https://openalex.org/W1601974704","https://openalex.org/W1997650413","https://openalex.org/W2012392077","https://openalex.org/W2080039641","https://openalex.org/W2095676919","https://openalex.org/W2105038027","https://openalex.org/W2114006755","https://openalex.org/W2117853077","https://openalex.org/W2119717200","https://openalex.org/W2123327324","https://openalex.org/W2123967136","https://openalex.org/W2127107099","https://openalex.org/W2129515556","https://openalex.org/W2132558143","https://openalex.org/W2136751544","https://openalex.org/W2148562281","https://openalex.org/W2155027007","https://openalex.org/W2164032318","https://openalex.org/W2165421048","https://openalex.org/W2168921921","https://openalex.org/W2180150039","https://openalex.org/W2277201334","https://openalex.org/W2319588593","https://openalex.org/W2914656440","https://openalex.org/W6653435097","https://openalex.org/W6674047710","https://openalex.org/W6678157427","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W1976483367","https://openalex.org/W1812381063","https://openalex.org/W2373034895","https://openalex.org/W2171128163","https://openalex.org/W2171968955","https://openalex.org/W155730701","https://openalex.org/W2360485332","https://openalex.org/W2542410050","https://openalex.org/W2352079541","https://openalex.org/W2161872510"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"is":[2,33],"an":[3],"essential":[4],"ability":[5],"for":[6,48,73],"robots":[7],"to":[8,25,44],"learn":[9],"new":[10],"motor":[11,74],"skills.":[12],"Nevertheless,":[13],"few":[14],"methods":[15],"scale":[16],"into":[17],"the":[18,31,60],"domain":[19],"of":[20,29,62],"anthropomorphic":[21],"robotics.":[22],"In":[23],"order":[24],"improve":[26],"in":[27],"terms":[28],"efficiency,":[30],"problem":[32],"reduced":[34],"onto":[35],"reward-weighted":[36],"imitation.":[37],"By":[38],"doing":[39],"so,":[40],"we":[41],"are":[42],"able":[43],"generate":[45],"a":[46,78,83],"framework":[47],"policy":[49],"learning":[50,56,76,90],"which":[51],"both":[52,72],"unifies":[53],"previous":[54],"reinforcement":[55],"approaches":[57],"and":[58,89],"allows":[59],"derivation":[61],"novel":[63],"algorithms.":[64],"We":[65],"show":[66],"our":[67],"two":[68],"most":[69],"relevant":[70],"applications":[71],"primitive":[75],"(e.g.,":[77],"complex":[79],"Ball-in-a-Cup":[80],"task":[81],"using":[82],"real":[84],"Barrett":[85],"WAM":[86],"robot":[87],"arm)":[88],"task-space":[91],"control.":[92]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}