{"id":"https://openalex.org/W4385488747","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191999","title":"Constrained Reinforcement Learning for Dynamic Material Handling","display_name":"Constrained Reinforcement Learning for Dynamic Material Handling","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488747","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191999"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5076937094","display_name":"Chengpeng Hu","orcid":"https://orcid.org/0000-0001-8343-4186"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengpeng Hu","raw_affiliation_strings":["Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology,Shenzhen,China","Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China","Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451882","display_name":"Ziming Wang","orcid":"https://orcid.org/0000-0002-3118-8742"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Wang","raw_affiliation_strings":["Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology,Shenzhen,China","Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China","Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456636","display_name":"Jialin Liu","orcid":"https://orcid.org/0000-0001-7047-8454"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Liu","raw_affiliation_strings":["Southern University of Science and Technology,Guangdong Key Laboratory of Brain-inspired Intelligent Computation,Department of Computer Science and Engineering,Shenzhen,China","Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China","Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Guangdong Key Laboratory of Brain-inspired Intelligent Computation,Department of Computer Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108704990","display_name":"Junyi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Wen","raw_affiliation_strings":["Huawei Technologies Co., Ltd,Trustworthiness Theory Research Center,Shenzhen,China","Trustworthiness Theory Research Center, Huawei Technologies Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd,Trustworthiness Theory Research Center,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Trustworthiness Theory Research Center, Huawei Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114053066","display_name":"Bifei Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bifei Mao","raw_affiliation_strings":["Huawei Technologies Co., Ltd,Trustworthiness Theory Research Center,Shenzhen,China","Trustworthiness Theory Research Center, Huawei Technologies Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd,Trustworthiness Theory Research Center,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Trustworthiness Theory Research Center, Huawei Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635494","display_name":"Xin Yao","orcid":"https://orcid.org/0000-0001-8837-4442"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yao","raw_affiliation_strings":["Southern University of Science and Technology,Guangdong Key Laboratory of Brain-inspired Intelligent Computation,Department of Computer Science and Engineering,Shenzhen,China","Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China","Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Guangdong Key Laboratory of Brain-inspired Intelligent Computation,Department of Computer Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Guangdong Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076937094"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.4153,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67723522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.9988999962806702,"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/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.9988999962806702,"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":0.9973999857902527,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7731648683547974},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6968080401420593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947795152664185},{"id":"https://openalex.org/keywords/lagrangian-relaxation","display_name":"Lagrangian relaxation","score":0.6104260087013245},{"id":"https://openalex.org/keywords/tardiness","display_name":"Tardiness","score":0.5462174415588379},{"id":"https://openalex.org/keywords/material-handling","display_name":"Material handling","score":0.5381406545639038},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5040413737297058},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3978109359741211},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.36445412039756775},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3022330105304718},{"id":"https://openalex.org/keywords/industrial-engineering","display_name":"Industrial engineering","score":0.25559234619140625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24896353483200073},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.20665395259857178},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20391041040420532}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7731648683547974},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6968080401420593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947795152664185},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.6104260087013245},{"id":"https://openalex.org/C2778047078","wikidata":"https://www.wikidata.org/wiki/Q82299449","display_name":"Tardiness","level":4,"score":0.5462174415588379},{"id":"https://openalex.org/C2983137510","wikidata":"https://www.wikidata.org/wiki/Q1413942","display_name":"Material handling","level":2,"score":0.5381406545639038},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5040413737297058},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3978109359741211},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.36445412039756775},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3022330105304718},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.25559234619140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24896353483200073},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.20665395259857178},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20391041040420532},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4565357659","display_name":null,"funder_award_id":"JCYJ20190809121403553","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G8890439619","display_name":null,"funder_award_id":"62250710682,61906083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1964181037","https://openalex.org/W1998510734","https://openalex.org/W2003746847","https://openalex.org/W2026899723","https://openalex.org/W2028316476","https://openalex.org/W2031672044","https://openalex.org/W2082474823","https://openalex.org/W2140153029","https://openalex.org/W2145339207","https://openalex.org/W2153327904","https://openalex.org/W2265549541","https://openalex.org/W2288790335","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2798885736","https://openalex.org/W2801499967","https://openalex.org/W2804791273","https://openalex.org/W2902429452","https://openalex.org/W2927317032","https://openalex.org/W2964043796","https://openalex.org/W2968147040","https://openalex.org/W2996896271","https://openalex.org/W2998619042","https://openalex.org/W3037164854","https://openalex.org/W3049468855","https://openalex.org/W3110506085","https://openalex.org/W3132026228","https://openalex.org/W3183892796","https://openalex.org/W3189576409","https://openalex.org/W3193936373","https://openalex.org/W3194012445","https://openalex.org/W3204752974","https://openalex.org/W4293545785","https://openalex.org/W6692846177","https://openalex.org/W6737893269","https://openalex.org/W6747473740","https://openalex.org/W6751725685","https://openalex.org/W6798240405"],"related_works":["https://openalex.org/W2011810134","https://openalex.org/W2050497389","https://openalex.org/W1568976062","https://openalex.org/W2960025371","https://openalex.org/W3097192092","https://openalex.org/W3029619930","https://openalex.org/W2061005265","https://openalex.org/W4400009772","https://openalex.org/W2997219294","https://openalex.org/W3083877676"],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,6,16,33,40,46,65,180],"the":[3,30,34,38,44,63,95,137,173,177],"core":[4],"parts":[5],"flexible":[7],"manufacturing":[8,35],"systems,":[9],"material":[10,26,71,147,168,200],"handling":[11,27,148],"involves":[12],"storage":[13],"and":[14,55,81,108,113,127,154,189,194],"transportation":[15],"materials":[17],"between":[18],"workstations":[19],"with":[20,139,156,185],"automated":[21,66],"vehicles.":[22],"The":[23],"improvement":[24],"in":[25,90],"can":[28,161],"impulse":[29],"overall":[31],"efficiency":[32],"system.":[36],"However,":[37],"occurrence":[39],"dynamic":[41,70,88,146,167],"events":[42,89],"during":[43],"optimisation":[45],"task":[47],"arrangements":[48],"poses":[49],"a":[50,98,144],"challenge":[51],"that":[52,123],"requires":[53],"adaptability":[54],"effectiveness.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"aim":[61],"at":[62],"scheduling":[64],"guided":[67],"vehicles":[68,110],"for":[69,166,199],"handling.":[72,169,201],"Motivated":[73],"by":[74],"some":[75],"real-world":[76],"scenarios,":[77],"unknown":[78],"new":[79],"tasks":[80],"unexpected":[82],"vehicle":[83],"breakdowns":[84],"are":[85],"regarded":[86],"as":[87,97,111,164],"our":[91,181],"problem.":[92],"We":[93],"formulate":[94],"problem":[96,138,158,174],"constrained":[99,119,188],"Markov":[100],"decision":[101],"process":[102],"which":[103,160],"takes":[104],"into":[105],"account":[106],"tardiness":[107],"available":[109],"cumulative":[112],"instantaneous":[114],"constraints,":[115],"respectively.":[116],"An":[117],"adaptive":[118],"reinforcement":[120,191],"learning":[121,192],"algorithm":[122],"combines":[124],"Lagrangian":[125],"relaxation":[126],"invalid":[128],"action":[129],"masking,":[130],"named":[131,150],"RCPOM,":[132],"is":[133,152],"proposed":[134,182],"to":[135],"address":[136],"two":[140],"hybrid":[141],"constraints.":[142],"Moreover,":[143],"gym-like":[145],"simulator,":[149],"DMH-GYM,":[151],"developed":[153],"equipped":[155],"diverse":[157],"instances,":[159],"be":[162],"used":[163,196],"benchmarks":[165],"Experimental":[170],"results":[171],"on":[172],"instances":[175],"demonstrate":[176],"outstanding":[178],"performance":[179],"approach":[183],"compared":[184],"eight":[186],"state-of-the-art":[187],"non-constrained":[190],"algorithms,":[193],"widely":[195],"dispatching":[197],"rules":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}