{"id":"https://openalex.org/W4391020520","doi":"https://doi.org/10.1109/cdc49753.2023.10384207","title":"Reinforcement Learning for Stochastic Max-Plus Linear Systems","display_name":"Reinforcement Learning for Stochastic Max-Plus Linear Systems","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020520","doi":"https://doi.org/10.1109/cdc49753.2023.10384207"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10384207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10384207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077747131","display_name":"Vignesh Subramanian","orcid":"https://orcid.org/0000-0003-3505-8483"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vignesh Subramanian","raw_affiliation_strings":["Georgia Institute of Technology,USA","Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078524654","display_name":"Farzaneh Farhadi","orcid":"https://orcid.org/0000-0003-0258-2764"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Farzaneh Farhadi","raw_affiliation_strings":["School of Engineering, Newcastle University,UK","School of Engineering, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Newcastle University,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Engineering, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017334634","display_name":"Sadegh Soudjani","orcid":"https://orcid.org/0000-0003-1922-6678"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sadegh Soudjani","raw_affiliation_strings":["School of Computing, Newcastle University,UK","School of Computing, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Newcastle University,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Computing, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"5631","last_page":"5638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11125","display_name":"Petri Nets in System Modeling","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11125","display_name":"Petri Nets in System Modeling","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11195","display_name":"Simulation Techniques and Applications","score":0.995199978351593,"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"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8066706657409668},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7801480293273926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.668893575668335},{"id":"https://openalex.org/keywords/uncountable-set","display_name":"Uncountable set","score":0.6357356309890747},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5678907632827759},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5675364136695862},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5457857847213745},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5370736122131348},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.47515246272087097},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4572224020957947},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4244951605796814},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4240010976791382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.344707727432251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25661802291870117},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1728019416332245}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8066706657409668},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7801480293273926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.668893575668335},{"id":"https://openalex.org/C142399903","wikidata":"https://www.wikidata.org/wiki/Q1128796","display_name":"Uncountable set","level":3,"score":0.6357356309890747},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5678907632827759},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5675364136695862},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5457857847213745},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5370736122131348},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.47515246272087097},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4572224020957947},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4244951605796814},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4240010976791382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.344707727432251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25661802291870117},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1728019416332245},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C110729354","wikidata":"https://www.wikidata.org/wiki/Q185478","display_name":"Countable set","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10384207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10384207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G3413121104","display_name":null,"funder_award_id":"EP/V043676/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5227039771","display_name":"CodeCPS: Correct-by-Design Estimation and Control of Cyber-Physical Systems","funder_award_id":"EP/V043676/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5447769386","display_name":null,"funder_award_id":"101089047","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W34706080","https://openalex.org/W1522301498","https://openalex.org/W1594201577","https://openalex.org/W1964585380","https://openalex.org/W1974274514","https://openalex.org/W1979349468","https://openalex.org/W2070773973","https://openalex.org/W2078233504","https://openalex.org/W2343349698","https://openalex.org/W2435384282","https://openalex.org/W2509841691","https://openalex.org/W2613835702","https://openalex.org/W2783183134","https://openalex.org/W2979955537","https://openalex.org/W3081872108","https://openalex.org/W3163100993","https://openalex.org/W3185247296","https://openalex.org/W3203995261","https://openalex.org/W4214717370","https://openalex.org/W4241372395","https://openalex.org/W4241496298","https://openalex.org/W4288774190","https://openalex.org/W4298857966","https://openalex.org/W6631190155","https://openalex.org/W6637967152"],"related_works":["https://openalex.org/W4388236136","https://openalex.org/W2807018115","https://openalex.org/W4200250224","https://openalex.org/W4246448622","https://openalex.org/W2126560268","https://openalex.org/W2285658092","https://openalex.org/W2482498454","https://openalex.org/W2947128950","https://openalex.org/W1996326480","https://openalex.org/W185460758"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,16,19,22,29,63,76,98,101,105,115,130,136,152],"design":[4],"of":[5,18,24,65,70,100,108,139,145],"control":[6,127,156],"policies":[7,128],"for":[8,129],"Discrete":[9],"Event":[10],"Systems":[11],"under":[12,97],"uncertainties.":[13],"We":[14],"capture":[15],"timing":[17,64],"events":[20,33],"using":[21],"framework":[23],"max-plus-linear":[25],"systems":[26],"in":[27,114,149],"which":[28],"time":[30],"between":[31],"consecutive":[32],"depends":[34],"on":[35,62,135],"random":[36],"delays":[37],"with":[38,46,151],"unknown":[39,106,111],"distributions.":[40],"Our":[41,132],"policy":[42],"synthesis":[43],"approach":[44,72,148],"is":[45,73],"respect":[47],"to":[48,58,74,79,122],"a":[49,80,93,140],"cost":[50],"function,":[51],"and":[52,91,125],"it":[53],"can":[54],"be":[55],"extended":[56],"directly":[57],"satisfy":[59],"safety":[60],"specifications":[61],"events.":[66],"The":[67],"main":[68],"novelty":[69],"our":[71,146],"translate":[75],"system":[77],"evolution":[78,99],"Markov":[81],"decision":[82],"process":[83],"(MDP)":[84],"that":[85],"has":[86],"an":[87],"uncountable":[88],"state":[89],"space":[90],"develop":[92],"stochastic":[94,153],"optimisation":[95],"problem":[96],"MDP.":[102],"To":[103],"tackle":[104],"distribution":[107],"uncertainties":[109],"(thus":[110],"transition":[112],"probabilities":[113],"MDP),":[116],"we":[117],"employ":[118],"model-free":[119],"reinforcement":[120],"learning":[121,147],"perform":[123],"optimisations":[124],"find":[126],"system.":[131],"implementation":[133],"results":[134],"9-dimensional":[137],"model":[138,154],"railway":[141],"network":[142],"show":[143],"superiority":[144],"comparison":[150],"predictive":[155],"approach.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}