{"id":"https://openalex.org/W2950226226","doi":"https://doi.org/10.1609/aaai.v33i01.33013739","title":"Hybrid Reinforcement Learning with Expert State Sequences","display_name":"Hybrid Reinforcement Learning with Expert State Sequences","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2950226226","doi":"https://doi.org/10.1609/aaai.v33i01.33013739","mag":"2950226226"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013739","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33013739","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051951021","display_name":"Xiaoxiao Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxiao Guo","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112248869","display_name":"Shiyu Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Chang","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101583277","display_name":"Mo Yu","orcid":"https://orcid.org/0000-0003-0949-6113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo Yu","raw_affiliation_strings":["IBM T. J. Watson"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113551673","display_name":"Gerald Tesauro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerald Tesauro","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045892503","display_name":"Murray Campbell","orcid":"https://orcid.org/0000-0001-8158-894X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murray Campbell","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"3739","last_page":"3746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8486130833625793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7355045676231384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7209579944610596},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.714339554309845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6599947810173035},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.641014039516449},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45038747787475586},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.4146539270877838},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06866303086280823}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8486130833625793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7355045676231384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209579944610596},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.714339554309845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6599947810173035},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.641014039516449},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45038747787475586},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.4146539270877838},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06866303086280823}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013739","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4259","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4259","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4259/4137","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013739","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013739","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1488730473","https://openalex.org/W1591675293","https://openalex.org/W1931877416","https://openalex.org/W1980035368","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2117675763","https://openalex.org/W2118688707","https://openalex.org/W2145339207","https://openalex.org/W2166302491","https://openalex.org/W2167224731","https://openalex.org/W2169498096","https://openalex.org/W2232454940","https://openalex.org/W2290104316","https://openalex.org/W2415726935","https://openalex.org/W2481567506","https://openalex.org/W2591957724","https://openalex.org/W2601322194","https://openalex.org/W2604726708","https://openalex.org/W2607198029","https://openalex.org/W2698595662","https://openalex.org/W2756826236","https://openalex.org/W2765308067","https://openalex.org/W2787053496","https://openalex.org/W2962787969","https://openalex.org/W2962996309","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963713397","https://openalex.org/W2963802910","https://openalex.org/W2963976294","https://openalex.org/W4211008118","https://openalex.org/W4300198501","https://openalex.org/W6646884813","https://openalex.org/W6684627452","https://openalex.org/W6718092244","https://openalex.org/W6751661917","https://openalex.org/W6780559895","https://openalex.org/W6808409006"],"related_works":["https://openalex.org/W2389542812","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2381894592","https://openalex.org/W4380318855","https://openalex.org/W2030629278","https://openalex.org/W4235667779","https://openalex.org/W2138720691","https://openalex.org/W2768698792","https://openalex.org/W4379251913"],"abstract_inverted_index":{"Existing":[0],"imitation":[1,83],"learning":[2,33,81,118],"approaches":[3],"often":[4],"require":[5],"that":[6,101],"the":[7,39,46,59,63,70,103,140],"complete":[8],"demonstration":[9],"data,":[10],"including":[11],"sequences":[12,41,111],"of":[13,42,62,69],"actions":[14,48,61],"and":[15,27,82,94,138],"states,":[16],"are":[17,49,105],"available.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"consider":[23],"a":[24,31,53,76],"more":[25],"realistic":[26],"difficult":[28],"scenario":[29],"where":[30],"reinforcement":[32,80,117],"agent":[34,71],"only":[35],"has":[36],"access":[37],"to":[38,57,107,112,129],"state":[40,65,109,151],"an":[43,91],"expert,":[44],"while":[45],"expert":[47,64,110,136,150],"unobserved.":[50],"We":[51,85],"propose":[52],"novel":[54],"tensor-based":[55,122],"model":[56,125],"infer":[58],"unobserved":[60],"sequences.":[66,152],"The":[67,97],"policy":[68,142],"is":[72,126,145],"then":[73],"optimized":[74],"via":[75],"hybrid":[77,88,141],"objective":[78,144],"combining":[79],"learning.":[84],"evaluated":[86],"our":[87,121],"approach":[89],"on":[90],"illustrative":[92],"domain":[93],"Atari":[95],"games.":[96],"empirical":[98],"results":[99],"show":[100],"(1)":[102],"agents":[104],"able":[106],"leverage":[108],"learn":[113],"faster":[114],"than":[115],"pure":[116],"baselines,":[119],"(2)":[120],"action":[123],"inference":[124],"advantageous":[127],"compared":[128],"standard":[130],"deep":[131],"neural":[132],"networks":[133],"in":[134,149],"inferring":[135],"actions,":[137],"(3)":[139],"optimization":[143],"robust":[146],"against":[147],"noise":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}