{"id":"https://openalex.org/W2097381193","doi":"https://doi.org/10.1109/iros.2003.1250666","title":"User-guided reinforcement learning of robot assistive tasks for an intelligent environment","display_name":"User-guided reinforcement learning of robot assistive tasks for an intelligent environment","publication_year":2004,"publication_date":"2004-07-08","ids":{"openalex":"https://openalex.org/W2097381193","doi":"https://doi.org/10.1109/iros.2003.1250666","mag":"2097381193"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2003.1250666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2003.1250666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5011561898","display_name":"Y. Wang","orcid":"https://orcid.org/0009-0006-6773-5935"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Huber","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038301640","display_name":"Vinay N. Papudesi","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V.N. Papudesi","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048183050","display_name":"Diane J. Cook","orcid":"https://orcid.org/0000-0002-4441-7508"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.J. Cook","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Texas Univ., Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"424","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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":0.9932000041007996,"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/T12288","display_name":"Optimization and Search Problems","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9836000204086304,"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/robot","display_name":"Robot","score":0.7784183025360107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7326215505599976},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.7203373312950134},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7042258977890015},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6409690380096436},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6341885328292847},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5538191795349121},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.5386644601821899},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5230235457420349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45807337760925293},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4559488892555237},{"id":"https://openalex.org/keywords/ubiquitous-robot","display_name":"Ubiquitous robot","score":0.4355211853981018},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.4311334192752838},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4305817484855652},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1538260281085968}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7784183025360107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326215505599976},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.7203373312950134},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7042258977890015},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6409690380096436},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6341885328292847},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5538191795349121},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.5386644601821899},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5230235457420349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45807337760925293},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4559488892555237},{"id":"https://openalex.org/C101188967","wikidata":"https://www.wikidata.org/wiki/Q7876552","display_name":"Ubiquitous robot","level":5,"score":0.4355211853981018},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.4311334192752838},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4305817484855652},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1538260281085968},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2003.1250666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2003.1250666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.5326","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.5326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ranger.uta.edu/~cook/pubs/iros03.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":18,"referenced_works":["https://openalex.org/W94457437","https://openalex.org/W175225925","https://openalex.org/W1497976081","https://openalex.org/W1585546346","https://openalex.org/W2009533501","https://openalex.org/W2059057465","https://openalex.org/W2122962140","https://openalex.org/W2131849699","https://openalex.org/W2146485332","https://openalex.org/W2158910349","https://openalex.org/W2161238807","https://openalex.org/W2622020362","https://openalex.org/W3011120880","https://openalex.org/W6603816613","https://openalex.org/W6607210333","https://openalex.org/W6635147684","https://openalex.org/W6683563453","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2493438666","https://openalex.org/W2134294860","https://openalex.org/W1965774354","https://openalex.org/W2724299411","https://openalex.org/W1901524571","https://openalex.org/W2640210118","https://openalex.org/W2133150803","https://openalex.org/W2151492375","https://openalex.org/W2076577081","https://openalex.org/W2147126435"],"abstract_inverted_index":{"Autonomous":[0],"robots":[1,46],"hold":[2],"the":[3,49,90],"possibility":[4],"of":[5,9,18,26,44,54,60,77,98,104],"performing":[6],"a":[7,42,55,61,80,93,105],"variety":[8],"assistive":[10],"tasks":[11],"in":[12,21],"intelligent":[13],"environments.":[14],"However,":[15],"widespread":[16],"use":[17,27],"robot":[19,35,56,62,94],"assistants":[20],"these":[22],"environments":[23],"requires":[24],"ease":[25],"by":[28],"individuals":[29],"who":[30],"are":[31],"generally":[32],"not":[33],"skilled":[34],"operators.":[36],"In":[37],"this":[38],"paper":[39],"we":[40,70],"present":[41],"method":[43],"training":[45],"that":[47,97],"bridges":[48],"gap":[50],"between":[51],"user":[52,72],"programming":[53],"and":[57],"autonomous":[58],"learning":[59],"task.":[63],"With":[64],"our":[65],"approach":[66],"to":[67,83],"variable":[68],"autonomy,":[69],"integrate":[71],"commands":[73],"at":[74],"varying":[75],"levels":[76],"abstraction":[78],"into":[79],"reinforcement":[81],"learner":[82],"permit":[84],"faster":[85],"policy":[86],"acquisition.":[87],"We":[88],"illustrate":[89],"ideas":[91],"using":[92],"assistant":[95],"task,":[96],"retrieving":[99],"medicine":[100],"for":[101],"an":[102],"inhabitant":[103],"smart":[106],"home.":[107]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}