{"id":"https://openalex.org/W4412877019","doi":"https://doi.org/10.1145/3711896.3737154","title":"THEMES: An Offline Apprenticeship Learning Framework for Evolving Reward Functions","display_name":"THEMES: An Offline Apprenticeship Learning Framework for Evolving Reward Functions","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877019","doi":"https://doi.org/10.1145/3711896.3737154"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737154","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737154","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035529894","display_name":"Xi Yang","orcid":"https://orcid.org/0000-0003-0026-9096"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Yang","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-0026-9096","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112878397","display_name":"Md Mirajul Islam","orcid":"https://orcid.org/0000-0001-5086-7399"},"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":"Md Mirajul Islam","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0000-0001-5086-7399","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779350","display_name":"Ge Gao","orcid":"https://orcid.org/0000-0002-3474-8637"},"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":"Ge Gao","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3474-8637","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"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":"https://orcid.org/0000-0003-1765-7837","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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3874,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88978823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3565","last_page":"3576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.927299976348877,"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":0.920199990272522,"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/apprenticeship","display_name":"Apprenticeship","score":0.7473151087760925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6639592051506042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45960572361946106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3781578540802002},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3513867259025574}],"concepts":[{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.7473151087760925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639592051506042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45960572361946106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3781578540802002},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3513867259025574},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737154","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737154","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737154","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3440589894","display_name":"Generalizing Data-Driven Technologies to Improve Individualized STEM Instruction by Intelligent Tutors","funder_award_id":"2013502","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G728260723","display_name":null,"funder_award_id":"#2013502, #1726550, #1660878, #1651909, and #1522107","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"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"},{"id":"https://openalex.org/G8632025160","display_name":"SCH: INT: Collaborative Research: S.E.P.S.I.S.: Sepsis Early Prediction Support Implementation System","funder_award_id":"1522107","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"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877019.pdf","grobid_xml":"https://content.openalex.org/works/W4412877019.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1976108485","https://openalex.org/W1991133427","https://openalex.org/W1993397663","https://openalex.org/W1999874108","https://openalex.org/W2010824638","https://openalex.org/W2047425368","https://openalex.org/W2055092429","https://openalex.org/W2119914747","https://openalex.org/W2145577370","https://openalex.org/W2280404143","https://openalex.org/W2402068992","https://openalex.org/W2559997609","https://openalex.org/W2626473047","https://openalex.org/W2742491462","https://openalex.org/W2807748885","https://openalex.org/W2808870406","https://openalex.org/W2862751544","https://openalex.org/W2883109840","https://openalex.org/W2903821316","https://openalex.org/W2964959375","https://openalex.org/W3012628688","https://openalex.org/W3037031609","https://openalex.org/W3101940057","https://openalex.org/W3108727463","https://openalex.org/W3188530841","https://openalex.org/W3188868777","https://openalex.org/W4213384663","https://openalex.org/W4281550900","https://openalex.org/W4283789863","https://openalex.org/W4285607140","https://openalex.org/W4292363360","https://openalex.org/W4298304654","https://openalex.org/W4299828299","https://openalex.org/W4299998725","https://openalex.org/W4380715556","https://openalex.org/W4382203560","https://openalex.org/W4385568314","https://openalex.org/W4392946780","https://openalex.org/W4401857047","https://openalex.org/W6757677476"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Apprenticeship":[0],"learning":[1],"(AL)":[2],"aims":[3],"to":[4],"induce":[5,94],"decision-making":[6],"policies":[7,35],"by":[8,47],"observing":[9],"and":[10,21,82,99],"imitating":[11],"expert":[12],"demonstrations.Existing":[13],"AL":[14,62],"approaches":[15],"typically":[16],"rely":[17],"on":[18],"online":[19],"interactions":[20],"assume":[22],"that":[23,51,90],"the":[24,44,72],"demonstrations":[25,45],"follow":[26],"a":[27,60,106],"single":[28],"reward":[29,49],"function.Nevertheless,":[30],"in":[31,39,76],"real-world":[32,111],"human-centric":[33,79,112],"applications,":[34],"are":[36],"usually":[37],"learned":[38],"an":[40],"offline":[41],"setting,":[42],"with":[43],"driven":[46],"multiple":[48,87],"functions":[50],"evolve":[52],"over":[53],"time.To":[54],"address":[55],"these":[56],"challenges,":[57],"we":[58],"introduce":[59],"novel":[61],"framework:":[63],"Time-aware":[64],"Hierarchical":[65],"EM":[66],"Energy-based":[67],"Sub-trajectory":[68],"(THEMES)":[69],"clustering.We":[70],"evaluate":[71],"effectiveness":[73],"of":[74,109],"THEMES":[75,91],"two":[77],"challenging":[78],"domains":[80],"-healthcare":[81],"education.Our":[83],"experimental":[84],"results":[85],"across":[86],"datasets":[88],"demonstrate":[89],"can":[92],"accurately":[93],"policies,":[95],"outperforming":[96],"competitive":[97],"baselines":[98],"ablations,":[100],"demonstrating":[101],"its":[102],"potential":[103],"for":[104],"tackling":[105],"broad":[107],"range":[108],"complex,":[110],"tasks.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}