{"id":"https://openalex.org/W2964407556","doi":"https://doi.org/10.24963/ijcai.2019/530","title":"Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human and Agent Demonstrations","display_name":"Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human and Agent Demonstrations","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964407556","doi":"https://doi.org/10.24963/ijcai.2019/530","mag":"2964407556"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/530","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/530","pdf_url":"https://www.ijcai.org/proceedings/2019/0530.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth 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/2019/0530.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":["School of EECS, Washington State University"],"raw_orcid":null,"affiliations":[{"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":["School of EECS, Washington State University"],"raw_orcid":null,"affiliations":[{"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":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3820","last_page":"3827"},"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":0.9986000061035156,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9883999824523926,"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":0.8511623740196228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.837209939956665},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8084659576416016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48601919412612915},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4232161343097687},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3668389320373535},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08564075827598572}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8511623740196228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837209939956665},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8084659576416016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48601919412612915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4232161343097687},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3668389320373535},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08564075827598572},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/530","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/530","pdf_url":"https://www.ijcai.org/proceedings/2019/0530.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/530","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/530","pdf_url":"https://www.ijcai.org/proceedings/2019/0530.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964407556.pdf","grobid_xml":"https://content.openalex.org/works/W2964407556.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W1971890413","https://openalex.org/W1986014385","https://openalex.org/W2031727428","https://openalex.org/W2061562262","https://openalex.org/W2097381042","https://openalex.org/W2113953866","https://openalex.org/W2115668428","https://openalex.org/W2125055259","https://openalex.org/W2137375617","https://openalex.org/W2148112459","https://openalex.org/W2159666783","https://openalex.org/W2164114810","https://openalex.org/W2174786457","https://openalex.org/W2237537322","https://openalex.org/W2491675558","https://openalex.org/W2560647685","https://openalex.org/W2625456521","https://openalex.org/W2735995851","https://openalex.org/W2739083961","https://openalex.org/W2740302738","https://openalex.org/W2950678851","https://openalex.org/W2962957031","https://openalex.org/W4214717370","https://openalex.org/W4297744728","https://openalex.org/W4298174377","https://openalex.org/W4312558117","https://openalex.org/W4319988532","https://openalex.org/W4394666657","https://openalex.org/W6601295022","https://openalex.org/W6643161839","https://openalex.org/W6755854181"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,113,145],"has":[2],"enjoyed":[3],"multiple":[4,111],"impressive":[5],"successes":[6,12],"in":[7,124],"recent":[8],"years.":[9],"However,":[10],"these":[11],"typically":[13],"require":[14],"very":[15],"large":[16],"amounts":[17],"of":[18,33,64,147],"data":[19],"before":[20,75],"an":[21,51],"agent":[22,52,102],"achieves":[23],"acceptable":[24],"performance.":[25,57],"This":[26,58],"paper":[27,47,59],"focuses":[28],"on":[29],"a":[30],"novel":[31],"way":[32],"combating":[34],"such":[35],"requirements":[36],"by":[37,87],"leveraging":[38],"existing":[39],"(human":[40],"or":[41],"agent)":[42],"knowledge.":[43],"In":[44],"particular,":[45],"this":[46,131],"leverages":[48,83],"demonstrations,":[49,141],"allowing":[50,100],"to":[53,103,137],"quickly":[54],"achieve":[55,121],"high":[56],"introduces":[60],"the":[61,70,84,92,96,101,105,144,148],"Dynamic":[62],"Reuse":[63],"Prior":[65],"(DRoP)":[66],"algorithm,":[67],"which":[68],"combines":[69],"offline":[71],"knowledge":[72,86,94],"(demonstrations":[73],"recorded":[74],"learning)":[76],"with":[77,110],"online":[78],"confidence-based":[79],"performance":[80,123,146],"analysis.":[81],"DRoP":[82,119],"demonstrator's":[85],"automatically":[88],"balancing":[89],"between":[90],"reusing":[91],"prior":[93],"and":[95,115],"current":[97],"learned":[98],"policy,":[99],"outperform":[104],"original":[106],"demonstrations.":[107],"We":[108],"compare":[109],"state-of-the-art":[112],"algorithms":[114],"empirically":[116],"show":[117,129],"that":[118,130],"can":[120,134],"superior":[122],"two":[125],"domains.":[126],"Additionally,":[127],"we":[128],"confidence":[132],"measure":[133],"be":[135],"used":[136],"selectively":[138],"request":[139],"additional":[140],"significantly":[142],"improving":[143],"agent.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}