{"id":"https://openalex.org/W3041575506","doi":"https://doi.org/10.24963/ijcai.2020/647","title":"Hierarchical Reinforcement Learning for Pedagogical Policy Induction (Extended Abstract)","display_name":"Hierarchical Reinforcement Learning for Pedagogical Policy Induction (Extended Abstract)","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3041575506","doi":"https://doi.org/10.24963/ijcai.2020/647","mag":"3041575506"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/647","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/647","pdf_url":"https://www.ijcai.org/proceedings/2020/0647.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth 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/2020/0647.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069371535","display_name":"Guojing Zhou","orcid":"https://orcid.org/0000-0002-9401-4854"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guojing Zhou","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027571540","display_name":"Hamoon Azizsoltani","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamoon Azizsoltani","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039146131","display_name":"Markel Sanz Ausin","orcid":"https://orcid.org/0000-0002-4526-9252"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Markel Sanz Ausin","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083076004","display_name":"Tiffany Barnes","orcid":"https://orcid.org/0000-0002-6500-9976"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiffany Barnes","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090231772","display_name":"Min Chi","orcid":"https://orcid.org/0000-0003-1765-7837"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Chi","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4691","last_page":"4695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9994999766349792,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9994999766349792,"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/T11122","display_name":"Online Learning and Analytics","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.987500011920929,"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":0.858094334602356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928141355514526},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.749478816986084},{"id":"https://openalex.org/keywords/tutor","display_name":"TUTOR","score":0.7446681261062622},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5430623292922974},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.47249165177345276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.461740106344223}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858094334602356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928141355514526},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.749478816986084},{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.7446681261062622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430623292922974},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.47249165177345276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.461740106344223},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/647","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/647","pdf_url":"https://www.ijcai.org/proceedings/2020/0647.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/647","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/647","pdf_url":"https://www.ijcai.org/proceedings/2020/0647.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G7965799476","display_name":"MetaDash: A Teacher Dashboard Informed by Real-Time Multichannel Self-Regulated Learning Data","funder_award_id":"1660878","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8332550026","display_name":"CAREER: Improving Adaptive Decision Making in Interactive Learning Environments","funder_award_id":"1651909","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3041575506.pdf","grobid_xml":"https://content.openalex.org/works/W3041575506.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W11018705","https://openalex.org/W1502922572","https://openalex.org/W1525421687","https://openalex.org/W1694248630","https://openalex.org/W1963697479","https://openalex.org/W2000976551","https://openalex.org/W2046109394","https://openalex.org/W2099038397","https://openalex.org/W2105715011","https://openalex.org/W2109388348","https://openalex.org/W2109910161","https://openalex.org/W2112564774","https://openalex.org/W2160178500","https://openalex.org/W2163640453","https://openalex.org/W2201581102","https://openalex.org/W2251007294","https://openalex.org/W2735325244","https://openalex.org/W2746553466","https://openalex.org/W2862751544","https://openalex.org/W2950323445","https://openalex.org/W2963177403","https://openalex.org/W2963262099","https://openalex.org/W2966387108"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2478195092","https://openalex.org/W4312351362","https://openalex.org/W2377919138","https://openalex.org/W2362145073","https://openalex.org/W2358338760","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359"],"abstract_inverted_index":{"In":[0,26,75],"interactive":[1],"e-learning":[2],"environments":[3],"such":[4],"as":[5],"Intelligent":[6],"Tutoring":[7],"Systems,":[8],"there":[9,29],"are":[10],"pedagogical":[11,55,96],"decisions":[12,56,66,100],"to":[13,92],"make":[14],"at":[15,101],"two":[16,71],"main":[17],"levels":[18,72],"of":[19,73],"granularity:":[20],"whole":[21],"problems":[22],"and":[23,80,104,127],"single":[24],"steps.":[25],"recent":[27],"years,":[28],"is":[30,116],"growing":[31],"interest":[32],"in":[33],"applying":[34],"data-driven":[35,50],"techniques":[36],"for":[37],"adaptive":[38],"decision":[39],"making":[40],"that":[41,64,98,112],"can":[42],"dynamically":[43],"tailor":[44],"students'":[45],"learning":[46],"experiences.":[47],"Most":[48],"existing":[49],"approaches,":[51],"however,":[52],"treat":[53],"these":[54,70],"equally,":[57],"or":[58],"independently,":[59],"disregarding":[60],"the":[61,113],"long-term":[62],"impact":[63],"tutor":[65],"may":[67],"have":[68],"across":[69],"granularity.":[74],"this":[76],"paper,":[77],"we":[78],"propose":[79],"apply":[81],"an":[82],"offline":[83],"Gaussian":[84],"Processes":[85],"based":[86],"Hierarchical":[87],"Reinforcement":[88],"Learning":[89],"(HRL)":[90],"framework":[91],"induce":[93],"a":[94,121,128],"hierarchical":[95],"policy":[97,115,126],"makes":[99],"both":[102],"problem":[103],"step":[105],"levels.":[106],"An":[107],"empirical":[108],"classroom":[109],"study":[110],"shows":[111],"HRL":[114],"significantly":[117],"more":[118],"effective":[119],"than":[120],"Deep":[122],"Q-Network":[123],"(DQN)":[124],"induced":[125],"random":[129],"yet":[130],"reasonable":[131],"baseline":[132],"policy.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}