{"id":"https://openalex.org/W7212190098","doi":"https://doi.org/10.1142/s0218001426400537","title":"Personalized Learning Path Identification and Multi-Objective Optimization Based on Knowledge-Tracing State Estimation and Constrained Reinforcement Learning","display_name":"Personalized Learning Path Identification and Multi-Objective Optimization Based on Knowledge-Tracing State Estimation and Constrained Reinforcement Learning","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212190098","doi":"https://doi.org/10.1142/s0218001426400537"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001426400537","doi":"https://doi.org/10.1142/s0218001426400537","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001426400537","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","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/A5016153958","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-4091-6035","observed_orcids":["https://orcid.org/0000-0002-4091-6035","https://orcid.org/0009-0007-3876-7097"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Yang","raw_affiliation_strings":["https://orcid.org/0009-0007-3876-7097"],"raw_orcid":"https://orcid.org/0009-0007-3876-7097","affiliations":[{"raw_affiliation_string":"https://orcid.org/0009-0007-3876-7097","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5151190999","display_name":"YingFei Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YingFei Huang","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]}],"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":0.74720012,"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":false,"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/T11122","display_name":"Online Learning and Analytics","score":0.0026000000070780516,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/personalized-learning-path-recommendation","display_name":"personalized learning path recommendation","score":0.9319999814033508},{"id":"https://openalex.org/keywords/knowledge-tracing","display_name":"knowledge tracing","score":0.953000009059906},{"id":"https://openalex.org/keywords/knowledge-state-estimation","display_name":"knowledge state estimation","score":0.8220000267028809},{"id":"https://openalex.org/keywords/constrained-reinforcement-learning","display_name":"constrained reinforcement learning","score":0.7400000095367432},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.9419999718666077},{"id":"https://openalex.org/keywords/action-masking","display_name":"action masking","score":0.6880000233650208},{"id":"https://openalex.org/keywords/long-term-retention","display_name":"long-term retention","score":0.7200000286102295},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.5389999747276306},{"id":"https://openalex.org/keywords/learning-efficiency","display_name":"learning efficiency","score":0.4399999976158142},{"id":"https://openalex.org/keywords/student-engagement","display_name":"student engagement","score":0.7509999871253967},{"id":"https://openalex.org/keywords/time-budget-constraints","display_name":"time budget constraints","score":0.5400000214576721}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7562000155448914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876000165939331},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6758999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6348999738693237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6087999939918518},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5491999983787537},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C3017813396","wikidata":"https://www.wikidata.org/wiki/Q17078173","display_name":"Resource constraints","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C2775907273","wikidata":"https://www.wikidata.org/wiki/Q7805281","display_name":"Time constraint","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001426400537","doi":"https://doi.org/10.1142/s0218001426400537","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001426400537","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.6164000034332275}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,33,40,188,201,204],"difficulty":[3,100],"of":[4,203],"simultaneously":[5],"considering":[6],"knowledge":[7,61,83,169],"state,":[8],"forgetting":[9,63],"risk,":[10,64],"and":[11,25,56,65,79,89,102,115,120,153,158,168,175,211],"pedagogical":[12],"constraints":[13,94],"in":[14,207],"personalized":[15],"learning-path":[16,42,127],"recommendation,":[17],"this":[18],"study":[19],"proposes":[20],"KTS-CMORL,":[21],"a":[22,131],"knowledge-tracing":[23,34],"state-estimation":[24,35],"constrained":[26,121],"multi-objective":[27],"reinforcement-learning":[28],"framework.":[29,44],"KTS-CMORL-KT":[30],"denotes":[31,39],"only":[32],"submodule,":[36],"whereas":[37,117],"KTS-CMORL":[38],"complete":[41],"optimization":[43,122],"The":[45],"model":[46],"integrates":[47],"resource":[48,103],"semantics,":[49],"response":[50],"performance,":[51],"behavioral":[52],"features,":[53],"time":[54,96],"intervals,":[55],"knowledge-graph":[57],"relations":[58],"to":[59,164,181,196],"estimate":[60],"mastery,":[62],"state":[66,209],"uncertainty.":[67],"Feasible":[68],"paths":[69],"are":[70,91,123],"identified":[71],"through":[72,125],"knowledge-gap":[73],"detection,":[74],"prerequisite":[75],"backtracking,":[76],"review-node":[77],"insertion,":[78],"action":[80],"masking,":[81],"while":[82,187],"gain,":[84],"long-term":[85],"retention,":[86],"learning":[87],"efficiency,":[88],"engagement":[90],"optimized":[92],"under":[93],"on":[95,109,137],"budget,":[97],"cognitive":[98],"load,":[99],"fluctuation,":[101],"repetition.":[104],"State-estimation":[105],"performance":[106],"is":[107],"evaluated":[108,124],"real":[110,138],"learner-interaction":[111],"records":[112],"from":[113,194],"RACE-H":[114],"Zhixue,":[116],"path":[118,213],"recommendation":[119],"offline":[126],"simulations":[128],"driven":[129],"by":[130,145,156,172,185],"frozen":[132],"GRU":[133],"learner":[134],"simulator":[135],"trained":[136],"logs.":[139],"Compared":[140],"with":[141,150],"AKT,":[142],"AUC":[143,152],"increases":[144],"2.2":[146],"percentage":[147,160,177],"points;":[148],"compared":[149],"RFKT,":[151],"ACC":[154],"increase":[155,171],"1.3":[157],"1.0":[159],"points,":[161,178],"respectively.":[162,179],"Relative":[163,180],"ELPR-DARL,":[165],"NDCG@10,":[166],"HR@10,":[167],"coverage":[170],"2.7,":[173],"3.6,":[174],"6.8":[176],"MORL,":[182],"HV":[183],"improves":[184],"9.2%,":[186],"overall":[189],"constraint":[190],"violation":[191],"rate":[192],"decreases":[193],"12.8%":[195],"1.8%.":[197],"These":[198],"results":[199],"demonstrate":[200],"effectiveness":[202],"proposed":[205],"framework":[206],"real-data":[208],"estimation":[210],"simulation-based":[212],"optimization.":[214]},"counts_by_year":[],"updated_date":"2026-09-24T07:57:37.273135","created_date":"2026-09-11T00:00:00"}