{"id":"https://openalex.org/W2740302738","doi":"https://doi.org/10.24963/ijcai.2017/422","title":"Improving Reinforcement Learning with Confidence-Based Demonstrations","display_name":"Improving Reinforcement Learning with Confidence-Based Demonstrations","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740302738","doi":"https://doi.org/10.24963/ijcai.2017/422","mag":"2740302738"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/422","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/422","pdf_url":"https://www.ijcai.org/proceedings/2017/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0422.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100641626","display_name":"Zhaodong Wang","orcid":"https://orcid.org/0000-0003-3112-077X"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaodong Wang","raw_affiliation_strings":["Washington State University","School of EECS Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]},{"raw_affiliation_string":"School of EECS Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070914351","display_name":"Matthew E. Taylor","orcid":"https://orcid.org/0000-0001-8946-0211"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew E. Taylor","raw_affiliation_strings":["Washington State University","School of EECS Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]},{"raw_affiliation_string":"School of EECS Washington State University","institution_ids":["https://openalex.org/I72951846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72951846"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3027","last_page":"3033"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.989799976348877,"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":0.989799976348877,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9761999845504761,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9010204076766968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.778597354888916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5509539842605591},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5471307039260864},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5181102156639099},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4971480667591095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44191431999206543},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.426643043756485},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11320170760154724},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10702446103096008}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9010204076766968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778597354888916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509539842605591},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5471307039260864},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5181102156639099},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4971480667591095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44191431999206543},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.426643043756485},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11320170760154724},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10702446103096008},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/422","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/422","pdf_url":"https://www.ijcai.org/proceedings/2017/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/422","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/422","pdf_url":"https://www.ijcai.org/proceedings/2017/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2754051857","display_name":null,"funder_award_id":"NNX16CD07C","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G2792800478","display_name":null,"funder_award_id":"2014-67021","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"},{"id":"https://openalex.org/G285167939","display_name":null,"funder_award_id":"IIS-1149917","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3040850200","display_name":"CAREER: A Multiagent Teacher/Student Framework for Sequential Decision Making Tasks","funder_award_id":"1149917","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3405304517","display_name":"EAGER:   Income Learning:   A New Model for Behavior-Analysis-Inspired Learning from Human Feedback","funder_award_id":"1643614","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5786867099","display_name":null,"funder_award_id":"IIS-1643614","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8109057036","display_name":null,"funder_award_id":"2014-67021-22174","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740302738.pdf","grobid_xml":"https://content.openalex.org/works/W2740302738.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1534477342","https://openalex.org/W1570448133","https://openalex.org/W1976115983","https://openalex.org/W1986014385","https://openalex.org/W2097381042","https://openalex.org/W2113913482","https://openalex.org/W2125055259","https://openalex.org/W2137375617","https://openalex.org/W2154018708","https://openalex.org/W2164114810","https://openalex.org/W2169659168","https://openalex.org/W2491675558","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4254755460"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2089013912","https://openalex.org/W2106552856","https://openalex.org/W2076061571","https://openalex.org/W2038908348","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,25,54,80,120],"has":[2],"had":[3],"many":[4],"successes,":[5],"but":[6],"in":[7,41,112,121],"practice":[8],"it":[9],"often":[10],"requires":[11],"significant":[12],"amounts":[13],"of":[14,100],"data":[15],"to":[16,23,27,33,45,53,62,104],"learn":[17],"high-performing":[18],"policies.":[19],"One":[20],"common":[21],"way":[22],"improve":[24,47,119],"is":[26,103],"allow":[28,58],"a":[29,35],"trained":[30],"(source)":[31],"agent":[32,61,71,86],"assist":[34],"new":[36],"(target)":[37],"agent.":[38,66],"The":[39,84,97],"goals":[40],"this":[42,101],"setting":[43],"are":[44],"1)":[46],"the":[48,59,64,77,89,108,113],"target":[49,60,85,109],"agent's":[50,79,91,110,115],"performance,":[51],"relative":[52],"unaided,":[55],"and":[56,93,127],"2)":[57],"outperform":[63],"source":[65,70,78,90,114],"Our":[67],"approach":[68],"leverages":[69],"demonstrations,":[72],"removing":[73],"any":[74],"requirements":[75],"on":[76],"algorithm":[81],"or":[82],"representation.":[83],"then":[87],"estimates":[88],"policy":[92,116],"improves":[94],"upon":[95],"it.":[96],"key":[98],"contribution":[99],"work":[102],"show":[105],"that":[106],"leveraging":[107],"uncertainty":[111],"can":[117],"significantly":[118],"two":[122],"complex":[123],"simulated":[124],"domains,":[125],"Keepaway":[126],"Mario.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}