{"id":"https://openalex.org/W7097718015","doi":null,"title":"Learning Pedagogical Policies from Few Training Data","display_name":"Learning Pedagogical Policies from Few Training Data","publication_year":2009,"publication_date":"2009-08-31","ids":{"openalex":"https://openalex.org/W7097718015"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.9830","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.9830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scalab.uc3m.es/~ffernand/papers/ecai06-rlates.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5070024418","display_name":"Ana Mar\u00eda Iglesias","orcid":"https://orcid.org/0000-0002-4685-5034","observed_orcids":["https://orcid.org/0000-0002-4685-5034","https://orcid.org/0000-0002-3042-1645"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ana Iglesias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Paloma Mart\u00ednez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paloma Mart\u00ednez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ricardo Aler","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricardo Aler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5142703171","display_name":"O Fern\u00e1ndez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"O Fern\u00e1ndez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5542023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9961000084877014,"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":0.9961000084877014,"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/T14414","display_name":"Artificial Intelligence in Education","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.000699999975040555,"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/adaptive-intelligent-tutoring-systems","display_name":"adaptive intelligent tutoring systems","score":0.7870000004768372},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7979999780654907},{"id":"https://openalex.org/keywords/simulated-students","display_name":"simulated students","score":0.9449999928474426},{"id":"https://openalex.org/keywords/expert-models","display_name":"expert models","score":0.5789999961853027},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9900000095367432},{"id":"https://openalex.org/keywords/database-design-education","display_name":"database design education","score":0.8119999766349792},{"id":"https://openalex.org/keywords/computer-science-education","display_name":"computer science education","score":0.48500001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670799970626831},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6557999849319458},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5181000232696533},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.9830","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.9830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scalab.uc3m.es/~ffernand/papers/ecai06-rlates.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.975600004196167,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2000976551","https://openalex.org/W2153657347","https://openalex.org/W4413072628","https://openalex.org/W2966712981","https://openalex.org/W4393152392","https://openalex.org/W3041575506","https://openalex.org/W2584516332","https://openalex.org/W4393159674","https://openalex.org/W7201922480","https://openalex.org/W4382567293"],"abstract_inverted_index":{"(AIES)":[0],"fits":[1],"as":[2,89],"a":[3,16,54,90,112],"Reinforcement":[4],"Learning":[5],"(RL)":[6],"problem.":[7],"However,":[8],"to":[9,14,28,46,52,65,72,108],"learn":[10,47,66],"pedagogical":[11,50,68,116],"policies":[12],"requires":[13],"acquire":[15],"huge":[17],"amount":[18],"of":[19,56,125,142],"experience":[20,63],"interacting":[21],"with":[22,79,102],"the":[23,29,62,67,98,103,109,123,140,143],"students,":[24,81,132],"so":[25],"applying":[26],"RL":[27,45],"AIES":[30,42,110],"from":[31],"scratch":[32],"is":[33,84,111,120,146],"infeasible.":[34],"In":[35],"this":[36],"paper":[37],"we":[38,70],"describe":[39],"RLATES,":[40],"an":[41,48,74,87,136],"that":[43,97,135],"uses":[44],"accurate":[49,114],"policy":[51],"teach":[53],"course":[55],"Data":[57],"Base":[58],"Design.":[59],"To":[60],"reduce":[61],"required":[64],"policy,":[69],"propose":[71],"use":[73],"initial":[75,115],"value":[76,99],"function":[77,100],"learned":[78,101],"simulated":[80,104],"whose":[82],"model":[83],"provided":[85],"by":[86],"expert":[88],"Markov":[91],"Decision":[92],"Process.":[93],"Empirical":[94],"results":[95],"demonstrate":[96],"students":[105],"and":[106,133],"transferred":[107],"very":[113],"policy.":[117],"The":[118],"evaluation":[119],"based":[121],"on":[122],"interaction":[124],"more":[126],"than":[127],"70":[128],"Computer":[129],"Science":[130],"undergraduate":[131],"demonstrates":[134],"efficient":[137],"guide":[138],"through":[139],"contents":[141],"educational":[144],"system":[145],"obtained.":[147],"1":[148]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}