{"id":"https://openalex.org/W2469544569","doi":"https://doi.org/10.1145/2930238.2930247","title":"Reinforcement Learning","display_name":"Reinforcement Learning","publication_year":2016,"publication_date":"2016-07-12","ids":{"openalex":"https://openalex.org/W2469544569","doi":"https://doi.org/10.1145/2930238.2930247","mag":"2469544569"},"language":"en","primary_location":{"id":"doi:10.1145/2930238.2930247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2930238.2930247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization","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/A5044625707","display_name":"Shitian Shen","orcid":"https://orcid.org/0000-0001-6859-5758"},"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":"Shitian Shen","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","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, Raleigh, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","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":1.553,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.85854969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"44"},"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":0.9973999857902527,"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":0.9973999857902527,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9847999811172485,"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":0.9793999791145325,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8609427213668823},{"id":"https://openalex.org/keywords/competence","display_name":"Competence (human resources)","score":0.7014786601066589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6805523633956909},{"id":"https://openalex.org/keywords/tutor","display_name":"TUTOR","score":0.6128917932510376},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48651546239852905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43184274435043335},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3681434690952301},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21317362785339355},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09308198094367981}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8609427213668823},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.7014786601066589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805523633956909},{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.6128917932510376},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48651546239852905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43184274435043335},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3681434690952301},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21317362785339355},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09308198094367981},{"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:10.1145/2930238.2930247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2930238.2930247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W15871483","https://openalex.org/W118320728","https://openalex.org/W174357488","https://openalex.org/W1196054003","https://openalex.org/W1493250243","https://openalex.org/W1514405275","https://openalex.org/W1525421687","https://openalex.org/W1564960024","https://openalex.org/W1963697479","https://openalex.org/W1971681797","https://openalex.org/W1974337957","https://openalex.org/W1980909828","https://openalex.org/W2000976551","https://openalex.org/W2056894129","https://openalex.org/W2090309761","https://openalex.org/W2099038397","https://openalex.org/W2105715011","https://openalex.org/W2116782019","https://openalex.org/W2153657347","https://openalex.org/W2408200822","https://openalex.org/W2461454659","https://openalex.org/W2574517116","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3147653952"],"related_works":["https://openalex.org/W2478195092","https://openalex.org/W4312351362","https://openalex.org/W2362145073","https://openalex.org/W2358338760","https://openalex.org/W183073912","https://openalex.org/W2119729863","https://openalex.org/W2887971028","https://openalex.org/W2501172308","https://openalex.org/W2365642790","https://openalex.org/W146785226"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"is":[3],"one":[4],"of":[5,28,41,56,130],"the":[6,26,30,39,54,89,104,108,131,136,158,173,179],"best":[7],"machine":[8],"learning":[9,120],"approaches":[10],"for":[11],"decision":[12,22],"making":[13,23],"in":[14,122],"interactive":[15],"environments.":[16],"RL":[17],"focuses":[18],"on":[19,48,77,88],"inducing":[20],"effective":[21,145,155],"policies":[24,50,58,106],"with":[25,154,169],"goal":[27],"maximizing":[29],"agent's":[31],"cumulative":[32],"reward.":[33],"In":[34,152],"this":[35],"study,":[36],"we":[37,68],"investigated":[38],"impact":[40],"both":[42],"immediate":[43],"and":[44,51,73,107],"delayed":[45],"reward":[46],"functions":[47],"RL-induced":[49],"empirically":[52],"evaluated":[53],"effectiveness":[55],"induced":[57,105],"within":[59],"an":[60],"Intelligent":[61],"Tutoring":[62],"System":[63],"called":[64],"Deep":[65],"Thought.":[66],"Moreover,":[67],"divided":[69],"students":[70],"into":[71],"Fast":[72,114],"Slow":[74,139],"learners":[75,115,140,160],"based":[76],"their":[78,84,165],"incoming":[79,110],"competence":[80],"as":[81,162,164],"measured":[82],"by":[83,135],"average":[85],"response":[86],"time":[87],"initial":[90],"tutorial":[91],"level.":[92],"Our":[93],"results":[94],"show":[95],"that":[96,123],"there":[97],"was":[98],"a":[99],"significant":[100],"interaction":[101],"effect":[102],"between":[103],"students'":[109],"competence.":[111],"More":[112],"specifically,":[113],"are":[116],"less":[117,177],"sensitive":[118],"to":[119],"environments":[121],"they":[124],"can":[125],"learn":[126],"equally":[127],"well":[128],"regardless":[129],"pedagogical":[132,146,156,171],"strategies":[133,147,157,172],"employed":[134],"tutor,":[137],"but":[138,168],"benefit":[141],"significantly":[142,176],"more":[143],"from":[144,149],"than":[148,178],"ineffective":[150,170],"ones.":[151],"fact,":[153],"slow":[159],"learned":[161,175],"much":[163],"faster":[166],"peers,":[167],"former":[174],"latter.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}