{"id":"https://openalex.org/W1965822678","doi":"https://doi.org/10.1109/iros.2013.6696816","title":"Learning sequential tasks interactively from demonstrations and own experience","display_name":"Learning sequential tasks interactively from demonstrations and own experience","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W1965822678","doi":"https://doi.org/10.1109/iros.2013.6696816","mag":"1965822678"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696816","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/A5010320027","display_name":"Kathrin Gr\u00e4ve","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Kathrin Grave","raw_affiliation_strings":["Intelligent Systems group, B-IT Research School, Germany","Dept. of Comput. Sci., Univ. of Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Systems group, B-IT Research School, Germany","institution_ids":[]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027761977","display_name":"Sven Behnke","orcid":"https://orcid.org/0000-0002-5040-7525"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Behnke","raw_affiliation_strings":["Intelligent Systems group, B-IT Research School, Germany","Dept. of Comput. Sci., Univ. of Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Systems group, B-IT Research School, Germany","institution_ids":[]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010320027"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0593663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"11","issue":null,"first_page":"3237","last_page":"3243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9948999881744385,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9948999881744385,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.963100016117096,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.917900025844574,"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":0.7272471785545349},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6922820806503296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6427750587463379},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6384410858154297},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6065924167633057},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5955339074134827},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5752165913581848},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5467024445533752},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5361364483833313},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.5321974158287048},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.48760905861854553},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48605042695999146},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4847123622894287},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45613083243370056},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.25871938467025757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272471785545349},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6922820806503296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6427750587463379},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6384410858154297},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6065924167633057},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5955339074134827},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5752165913581848},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5467024445533752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5361364483833313},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.5321974158287048},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.48760905861854553},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48605042695999146},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4847123622894287},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45613083243370056},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.25871938467025757},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2013.6696816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696816","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:10.1.1.416.9966","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.416.9966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ais.uni-bonn.de/papers/IROS_2013_Graeve.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W164706946","https://openalex.org/W304821478","https://openalex.org/W1480643256","https://openalex.org/W1746819321","https://openalex.org/W1925816294","https://openalex.org/W1963873191","https://openalex.org/W1986014385","https://openalex.org/W2002489204","https://openalex.org/W2008662704","https://openalex.org/W2032277247","https://openalex.org/W2036096913","https://openalex.org/W2060914855","https://openalex.org/W2088038240","https://openalex.org/W2134146570","https://openalex.org/W2151238122","https://openalex.org/W2156949391","https://openalex.org/W2167340365","https://openalex.org/W3005581722","https://openalex.org/W4211049957","https://openalex.org/W4285719527","https://openalex.org/W6640290305"],"related_works":["https://openalex.org/W3104422856","https://openalex.org/W4206864338","https://openalex.org/W4287867179","https://openalex.org/W3134690064","https://openalex.org/W4210726438","https://openalex.org/W4287752080","https://openalex.org/W3118984993","https://openalex.org/W3037706579","https://openalex.org/W4401389295","https://openalex.org/W3157580548"],"abstract_inverted_index":{"Deploying":[0],"robots":[1,43],"to":[2,8,12,19,25,30,41,53,56,61,81,109,141,153,192,212],"our":[3,98,129,210],"day-to-day":[4],"life":[5],"requires":[6],"them":[7],"have":[9],"the":[10,124,171,198,207],"ability":[11,208],"learn":[13,54,214],"from":[14,89,134,200],"their":[15,67,112,116],"environment":[16],"in":[17,59,218],"order":[18,60],"acquire":[20,82],"new":[21],"task":[22,224],"knowledge":[23],"and":[24,92,136,160],"flexibly":[26],"adapt":[27],"existing":[28],"skills":[29],"various":[31,219],"situations.":[32],"For":[33],"typical":[34],"real-world":[35],"tasks,":[36],"it":[37],"is":[38,146],"not":[39],"sufficient":[40],"endow":[42],"with":[44,202],"a":[45,63,79,119,149,179,184,222],"set":[46],"of":[47,84,103,123,158,167,174,209],"primitive":[48],"actions.":[49],"Rather,":[50],"they":[51],"need":[52],"how":[55],"sequence":[57,126],"these":[58],"achieve":[62],"desired":[64],"effect":[65],"on":[66,148,221],"environment.":[68],"In":[69,95],"this":[70],"paper,":[71],"we":[72,151,177],"propose":[73],"an":[74],"intuitive":[75],"learning":[76,88,104,191],"method":[77],"for":[78,155],"robot":[80,199],"sequences":[83,140,162,195,201,217],"motions":[85],"by":[86],"combining":[87],"human":[90],"demonstrations":[91],"reinforcement":[93],"learning.":[94],"every":[96],"situation,":[97],"approach":[99,130,211],"treats":[100],"both":[101],"ways":[102],"as":[105,163,165],"alternative":[106],"control":[107],"flows":[108],"optimally":[110],"exploit":[111],"strengths":[113],"without":[114],"inheriting":[115],"shortcomings.":[117],"Using":[118],"Gaussian":[120],"Process":[121],"approximation":[122,145],"state-action":[125],"value":[127,175],"function,":[128],"generalizes":[131],"values":[132],"observed":[133],"demonstrated":[135],"autonomously":[137],"generated":[138],"action":[139,161,194,216],"unknown":[142],"inputs.":[143],"This":[144],"based":[147],"kernel":[150],"designed":[152],"account":[154],"different":[156],"representations":[157],"tasks":[159],"well":[164],"inputs":[166],"variable":[168],"length.":[169],"From":[170],"expected":[172],"deviation":[173],"estimates,":[176],"devise":[178],"greedy":[180],"exploration":[181],"policy":[182],"following":[183],"Bayesian":[185],"optimization":[186],"criterion":[187],"that":[188],"quickly":[189],"converges":[190],"promising":[193],"while":[196],"protecting":[197],"unpredictable":[203],"outcome.":[204],"We":[205],"demonstrate":[206],"efficiently":[213],"appropriate":[215],"situations":[220],"manipulation":[223],"involving":[225],"stacked":[226],"boxes.":[227]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}