{"id":"https://openalex.org/W2251007294","doi":"https://doi.org/10.5555/2615731.2617417","title":"Offline policy evaluation across representations with applications to educational games","display_name":"Offline policy evaluation across representations with applications to educational games","alternate_titles":[],"publication_year":2014,"publication_date":"2014-05-05","ids":{"openalex":"https://openalex.org/W2251007294","doi":"https://doi.org/10.5555/2615731.2617417","mag":"2251007294"},"language":"en","primary_location":{"id":"mag:2251007294","doi":"https://doi.org/10.5555/2615731.2617417","is_oa":false,"landing_page_url":"https://www.ifaamas.org/Proceedings/aamas2014/aamas/p1077.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Adaptive Agents and Multi-Agents Systems","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2251007294"],"child_works_count":0,"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/A5013700590","display_name":"Travis Mandel","orcid":"https://orcid.org/0000-0003-3127-4429","observed_orcids":["https://orcid.org/0000-0003-3127-4429"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Travis Mandel","raw_affiliation_strings":["Univ. of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3127-4429","affiliations":[{"raw_affiliation_string":"Univ. of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113558958","display_name":"Yun-En Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-En Liu","raw_affiliation_strings":["Univ. of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743","observed_orcids":["https://orcid.org/0000-0001-6764-2743"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Stanford Univ., Stanford, CA (USA)"],"raw_orcid":"https://orcid.org/0000-0001-6764-2743","affiliations":[{"raw_affiliation_string":"Stanford Univ., Stanford, CA (USA)","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084989076","display_name":"Emma Brunskill","orcid":"https://orcid.org/0000-0002-3971-7127","observed_orcids":["https://orcid.org/0000-0002-3971-7127"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emma Brunskill","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh PA USA"],"raw_orcid":"https://orcid.org/0000-0002-3971-7127","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh PA USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050910253","display_name":"Zoran Popovi\u0107","orcid":"https://orcid.org/0000-0001-5989-3016","observed_orcids":["https://orcid.org/0000-0001-5989-3016"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoran Popovi\u0107","raw_affiliation_strings":["Univ. of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5989-3016","affiliations":[{"raw_affiliation_string":"Univ. of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1436,"has_fulltext":false,"cited_by_count":162,"citation_normalized_percentile":{"value":0.95690784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1077","last_page":"1084"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9463000297546387,"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":0.9463000297546387,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.045099999755620956,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/offline-policy-evaluation","display_name":"offline policy evaluation","score":0.9869999885559082},{"id":"https://openalex.org/keywords/policy-representation","display_name":"policy representation","score":0.6629999876022339},{"id":"https://openalex.org/keywords/educational-games","display_name":"game-based learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/adaptive-sequencing","display_name":"adaptive sequencing","score":0.5669999718666077},{"id":"https://openalex.org/keywords/student-engagement","display_name":"student engagement","score":0.8889999985694885},{"id":"https://openalex.org/keywords/partially-observable-environments","display_name":"partially observable environments","score":0.5759999752044678},{"id":"https://openalex.org/keywords/high-dimensional-state-spaces","display_name":"high-dimensional state spaces","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7909748554229736},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7368589043617249},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7241170406341553},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5741888880729675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5548111200332642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329286456108093},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43605583906173706},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.4325034022331238},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42056983709335327},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2251007294","doi":"https://doi.org/10.5555/2615731.2617417","is_oa":false,"landing_page_url":"https://www.ifaamas.org/Proceedings/aamas2014/aamas/p1077.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Adaptive Agents and Multi-Agents Systems","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.657.1178","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.657.1178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homes.cs.washington.edu/%7Eyunliu/papers/aamas2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.6164000034332275}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W91593682","https://openalex.org/W1484113995","https://openalex.org/W1514405275","https://openalex.org/W1514587017","https://openalex.org/W1520028013","https://openalex.org/W1539216098","https://openalex.org/W1657674574","https://openalex.org/W1681299129","https://openalex.org/W1949804828","https://openalex.org/W2002748013","https://openalex.org/W2027106130","https://openalex.org/W2099430963","https://openalex.org/W2120346334","https://openalex.org/W2130005627","https://openalex.org/W2131600418","https://openalex.org/W2138909795","https://openalex.org/W2151161180","https://openalex.org/W2158282517","https://openalex.org/W2160328579","https://openalex.org/W2161523118","https://openalex.org/W2253356247","https://openalex.org/W2398027007","https://openalex.org/W2495707668"],"related_works":["https://openalex.org/W4285778253","https://openalex.org/W4393161321","https://openalex.org/W3124245472","https://openalex.org/W4381250544","https://openalex.org/W2563736478","https://openalex.org/W7083594191","https://openalex.org/W4393284040","https://openalex.org/W4285483887","https://openalex.org/W4382322484","https://openalex.org/W7133215161"],"abstract_inverted_index":{"Consider":[0],"an":[1,148],"autonomous":[2],"teacher":[3],"agent":[4,19],"trying":[5,20],"to":[6,10,21,25,67,79,93,121,131,133,140,176],"adaptively":[7],"sequence":[8],"material":[9],"best":[11,47],"keep":[12],"a":[13,17,41,107,141,158],"student":[14,61],"engaged,":[15],"or":[16],"med-ical":[18],"help":[22],"suggest":[23],"treatments":[24],"maximize":[26],"patient":[27],"outcomes.":[28],"To":[29],"solve":[30],"these":[31],"complex":[32],"reinforcement":[33],"learning":[34],"problems,":[35],"we":[36,105,156],"must":[37,89],"first":[38],"decide":[39],"on":[40,125,168],"policy":[42,130,166,186],"repre-sentation.":[43],"But":[44],"determining":[45],"the":[46,53,126,173,183],"representation":[48],"can":[49],"be":[50],"challenging,":[51],"since":[52],"environment":[54],"includes":[55],"many":[56],"poorly-understood":[57],"processes":[58],"(such":[59],"as":[60],"engagement)":[62],"and":[63,95,112,123,180,193],"is":[64,118],"therefore":[65],"difficult":[66],"accurately":[68],"simulate.":[69],"These":[70],"domains":[71],"are":[72],"also":[73],"high":[74],"stakes,":[75],"making":[76],"it":[77],"infeasible":[78],"evaluate":[80,96],"candi-date":[81],"representations":[82],"by":[83,152,201],"running":[84],"them":[85],"online.":[86],"Instead,":[87],"one":[88],"leverage":[90],"existing":[91],"data":[92],"learn":[94],"new":[97,134],"poli-cies":[98],"for":[99,110],"future":[100],"use.":[101],"In":[102],"this":[103,138,169],"paper,":[104],"present":[106],"data-driven":[108],"methodology":[109,139],"comparing":[111],"validating":[113],"policies":[114,175],"offline.":[115],"Our":[116],"method":[117,162],"unbiased,":[119],"agnostic":[120],"representation,":[122],"fo-cuses":[124],"ability":[127],"of":[128],"each":[129],"generalize":[132],"data.":[135],"We":[136,171],"apply":[137],"partially-observable,":[142],"high-dimensional":[143],"concept":[144],"sequencing":[145],"problem":[146],"in":[147],"educational":[149],"game.":[150],"Guided":[151],"our":[153,197],"evaluation":[154],"methodology,":[155],"propose":[157],"novel":[159],"feature":[160],"compaction":[161],"that":[163,182],"substantially":[164],"im-proves":[165],"performance":[167],"problem.":[170],"deploy":[172],"best-performing":[174],"2,000":[177],"real":[178],"students":[179],"show":[181],"learned":[184],"adaptive":[185],"shows":[187],"statistically":[188],"significant":[189],"im-provement":[190],"over":[191],"random":[192],"expert":[194],"baselines,":[195],"improving":[196],"achievement-based":[198],"reward":[199],"measure":[200],"32%.":[202]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2251007294","counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":7}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
