{"id":"https://openalex.org/W4414433174","doi":"https://doi.org/10.1109/case58245.2025.11163782","title":"Extended Invalid Action Mask: Training-Time Size-Agnostic Safe Reinforcement Learning for Flexible Job Shop Scheduling Problems","display_name":"Extended Invalid Action Mask: Training-Time Size-Agnostic Safe Reinforcement Learning for Flexible Job Shop Scheduling Problems","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414433174","doi":"https://doi.org/10.1109/case58245.2025.11163782"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"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/A5078710866","display_name":"Weilin Cai","orcid":"https://orcid.org/0000-0001-7508-7567"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weilin Cai","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Science and Engineering,Guangdong,China,518172"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Science and Engineering,Guangdong,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112672304","display_name":"Wenjun Zheng","orcid":"https://orcid.org/0009-0009-4981-0219"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zheng","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110516470","display_name":"Zhaoli Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoli Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yilan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilan Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050195423","display_name":"Jianfeng Mao","orcid":"https://orcid.org/0000-0002-8969-0284"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Mao","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Guangdong,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078710866"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35080517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"351","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T12782","display_name":"Assembly Line Balancing Optimization","score":0.9706000089645386,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T14011","display_name":"Elevator Systems and Control","score":0.9589999914169312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7059999704360962},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5795999765396118},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.5471000075340271},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4977000057697296},{"id":"https://openalex.org/keywords/job-shop","display_name":"Job shop","score":0.46939998865127563},{"id":"https://openalex.org/keywords/flow-shop-scheduling","display_name":"Flow shop scheduling","score":0.34929999709129333},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.32269999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587000131607056},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7059999704360962},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.5471000075340271},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C2777243215","wikidata":"https://www.wikidata.org/wiki/Q1493226","display_name":"Job shop","level":5,"score":0.46939998865127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C158336966","wikidata":"https://www.wikidata.org/wiki/Q3074426","display_name":"Flow shop scheduling","level":4,"score":0.34929999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2780682718","wikidata":"https://www.wikidata.org/wiki/Q16321575","display_name":"Production control","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C112866106","wikidata":"https://www.wikidata.org/wiki/Q267053","display_name":"Lottery scheduling","level":5,"score":0.2904999852180481},{"id":"https://openalex.org/C127456818","wikidata":"https://www.wikidata.org/wiki/Q238879","display_name":"Rate-monotonic scheduling","level":4,"score":0.28600001335144043},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11163782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W964861289","https://openalex.org/W1967955864","https://openalex.org/W1984200231","https://openalex.org/W1995015596","https://openalex.org/W2000099188","https://openalex.org/W2000946059","https://openalex.org/W2007315235","https://openalex.org/W2046437335","https://openalex.org/W2057285547","https://openalex.org/W2111244700","https://openalex.org/W2122736695","https://openalex.org/W2900715471","https://openalex.org/W2963696152","https://openalex.org/W2973930420","https://openalex.org/W2997053847","https://openalex.org/W2997791715","https://openalex.org/W3037164854","https://openalex.org/W3082377584","https://openalex.org/W3092208345","https://openalex.org/W3215848916","https://openalex.org/W4244166692","https://openalex.org/W4253180363","https://openalex.org/W4255512601","https://openalex.org/W4285024875","https://openalex.org/W4309345803","https://openalex.org/W4377695412","https://openalex.org/W4386590783","https://openalex.org/W4402402057","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"The":[0],"flexible":[1],"job":[2,22],"shop":[3,23],"scheduling":[4,24,123],"problem":[5,10,90],"(FJSP)":[6],"is":[7,141],"an":[8,97],"NP-hard":[9],"in":[11,31,46],"which":[12],"machine":[13],"assignments":[14],"are":[15],"additionally":[16],"considered":[17],"compared":[18],"to":[19,120],"the":[20,40,133],"classical":[21],"problem.":[25],"It":[26],"has":[27,54],"received":[28],"increased":[29],"attention":[30],"recent":[32],"years,":[33],"as":[34],"its":[35],"global":[36],"hard":[37],"constraints":[38],"highlight":[39],"importance":[41],"of":[42],"policy":[43,79],"safety,":[44],"especially":[45],"real":[47],"production":[48,146],"contexts.":[49],"Deep":[50],"reinforcement":[51],"learning":[52],"(DRL)":[53],"become":[55],"a":[56],"popular":[57],"method":[58],"for":[59,145],"solving":[60],"FJSP;":[61],"however,":[62],"ensuring":[63],"both":[64],"size-agnostic":[65],"and":[66,117,124,143],"safety-guaranteed":[67],"properties":[68],"during":[69],"training":[70,87],"remains":[71],"challenging.":[72],"Penalty-based":[73],"approaches":[74],"allow":[75],"infeasible":[76],"actions,":[77],"degrading":[78],"quality,":[80],"while":[81,108],"standard":[82],"invalid":[83],"action":[84,111,118],"masking":[85],"prevents":[86],"across":[88,105],"different":[89],"sizes.":[91],"To":[92],"address":[93],"this,":[94],"we":[95],"propose":[96],"extended":[98],"action-masking":[99],"mechanism":[100],"that":[101,138],"maintains":[102],"semantic":[103],"consistency":[104],"varying":[106],"scales":[107],"strictly":[109],"enforcing":[110],"feasibility.":[112],"Our":[113],"framework":[114],"integrates":[115],"state":[116],"embeddings":[119],"support":[121],"adaptive":[122],"multi-scale":[125],"training.":[126],"Empirical":[127],"results":[128],"demonstrate":[129],"improved":[130],"performance":[131],"over":[132],"latest":[134],"DRL-based":[135],"methods,":[136],"indicating":[137],"our":[139],"approach":[140],"scalable":[142],"robust":[144],"scheduling.":[147]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}