{"id":"https://openalex.org/W2606546905","doi":"https://doi.org/10.1145/3049797.3049827","title":"Controller Synthesis for Reward Collecting Markov Processes in Continuous Space","display_name":"Controller Synthesis for Reward Collecting Markov Processes in Continuous Space","publication_year":2017,"publication_date":"2017-04-13","ids":{"openalex":"https://openalex.org/W2606546905","doi":"https://doi.org/10.1145/3049797.3049827","mag":"2606546905"},"language":"en","primary_location":{"id":"doi:10.1145/3049797.3049827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3049797.3049827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Hybrid Systems: Computation and Control","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/A5017334634","display_name":"Sadegh Soudjani","orcid":"https://orcid.org/0000-0003-1922-6678"},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sadegh Esmaeil Zadeh Soudjani","raw_affiliation_strings":["Max Planck Institute for Software Systems, Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Software Systems, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I4210121786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081010207","display_name":"Rupak Majumdar","orcid":"https://orcid.org/0000-0003-2136-0542"},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rupak Majumdar","raw_affiliation_strings":["Max Planck Institute for Software Systems, Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Software Systems, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I4210121786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017334634"],"corresponding_institution_ids":["https://openalex.org/I4210121786"],"apc_list":null,"apc_paid":null,"fwci":1.2459,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84741907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T12288","display_name":"Optimization and Search Problems","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/markov-decision-process","display_name":"Markov decision process","score":0.8928515315055847},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6945564150810242},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6256967782974243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5883582234382629},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5817642211914062},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.5518989562988281},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5361537933349609},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5128734111785889},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.46366479992866516},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46012353897094727},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.44636061787605286},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4371623694896698},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4167234003543854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30476582050323486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2333071231842041},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11568829417228699}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8928515315055847},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6945564150810242},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6256967782974243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5883582234382629},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5817642211914062},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.5518989562988281},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5361537933349609},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5128734111785889},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.46366479992866516},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46012353897094727},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.44636061787605286},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4371623694896698},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4167234003543854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30476582050323486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2333071231842041},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11568829417228699},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3049797.3049827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3049797.3049827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Hybrid Systems: Computation and Control","raw_type":"proceedings-article"},{"id":"pmh:oai:escidoc.org:escidoc:2564943","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0000-EBD2-A","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W70930922","https://openalex.org/W1512937499","https://openalex.org/W1529558080","https://openalex.org/W1859458367","https://openalex.org/W1980146067","https://openalex.org/W1993112505","https://openalex.org/W2010654234","https://openalex.org/W2017419329","https://openalex.org/W2018087463","https://openalex.org/W2084772009","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2171282796","https://openalex.org/W2172283073","https://openalex.org/W2334782222","https://openalex.org/W2963555463","https://openalex.org/W4245744559"],"related_works":["https://openalex.org/W2807018115","https://openalex.org/W4388236136","https://openalex.org/W4200250224","https://openalex.org/W2126560268","https://openalex.org/W2285658092","https://openalex.org/W2482498454","https://openalex.org/W2947128950","https://openalex.org/W3087810330","https://openalex.org/W1996326480","https://openalex.org/W185460758"],"abstract_inverted_index":{"We":[0,177,199],"propose":[1],"and":[2,71,89,106,164,183,249,288],"analyze":[3],"a":[4,35,74,93,100,104,127,134,221,233,274],"generic":[5],"mathematical":[6],"model":[7,21,50],"for":[8,103,187,224],"optimizing":[9],"rewards":[10,78,154,171],"in":[11,27,59,123,159,172,263,284],"continuous-space,":[12],"dynamic":[13,206],"environments,":[14],"called":[15],"Reward":[16],"Collecting":[17],"Markov":[18,56,237,247],"Processes.":[19],"Our":[20,49],"is":[22,32,64,95,99,115,126,148],"motivated":[23],"by":[24,67,145,297],"request-serving":[25],"applications":[26],"robotics,":[28],"where":[29],"the":[30,61,68,83,107,112,119,138,146,149,157,160,165,173,180,189,192,229,246,253,261,268,279,285,291],"objective":[31],"to":[33,38,40,117,205],"control":[34,130],"dynamical":[36],"system":[37],"respond":[39],"stochastically":[41],"generated":[42],"environment":[43],"requests,":[44],"while":[45],"minimizing":[46],"wait":[47],"times.":[48],"departs":[51],"from":[52],"usual":[53],"discounted":[54],"reward":[55,62,94,111,143,236,283],"decision":[57,238],"processes":[58],"that":[60,257],"function":[63],"not":[65],"determined":[66],"current":[69],"state":[70,140],"action.":[72],"Instead,":[73],"background":[75],"process":[76,248],"generates":[77],"whose":[79],"values":[80],"depend":[81],"on":[82,252,267],"number":[84],"of":[85,129,152,169,242,245,278],"steps":[86],"between":[87],"generation":[88],"collection.":[90],"For":[91],"example,":[92],"declared":[96],"whenever":[97],"there":[98],"new":[101],"request":[102],"robot":[105,108],"gets":[109],"higher":[110],"sooner":[113],"it":[114],"able":[116],"serve":[118],"request.":[120],"A":[121],"policy":[122],"this":[124],"setting":[125],"sequence":[128],"actions":[131],"which":[132,213,227],"determines":[133],"(random)":[135],"trajectory":[136,147],"over":[137,208],"continuous":[139],"space.":[141],"The":[142],"achieved":[144],"cumulative":[150],"sum":[151],"all":[153,170],"obtained":[155,296],"along":[156],"way":[158],"finite":[161,181],"horizon":[162,175,182,185],"case":[163],"long":[166,193],"run":[167,194],"average":[168,195],"infinite":[174,184,286],"case.":[176],"study":[178],"both":[179],"problems":[186,202,226],"maximizing":[188],"expected":[190,281],"(respectively,":[191],"expected)":[196],"collected":[197,282],"reward.":[198],"characterize":[200],"these":[201,225],"as":[203],"solutions":[204,266],"programs":[207],"an":[209],"augmented":[210],"hybrid":[211],"space,":[212],"gives":[214],"history-dependent":[215],"optimal":[216,265,280],"policies.":[217],"Second,":[218],"we":[219,255,258,272],"provide":[220,273],"computational":[222],"method":[223],"abstracts":[228],"continuous-space":[230],"problem":[231],"into":[232],"discrete-space":[234],"collecting":[235],"process.":[239],"Under":[240],"assumptions":[241],"Lipschitz":[243],"continuity":[244],"uniform":[250],"bounds":[251],"discounting,":[254],"show":[256,289],"can":[259,294],"bound":[260],"error":[262],"computing":[264],"finite-state":[269],"approximation.":[270],"Finally,":[271],"fixed":[275,292],"point":[276,293],"characterization":[277],"case,":[287],"how":[290],"be":[295],"value":[298],"iteration.":[299]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}