{"id":"https://openalex.org/W7159767802","doi":"https://doi.org/10.1002/net.70039","title":"Shaping Decision Models for Stochastic Dynamic Optimization Problems via Reinforcement Learning","display_name":"Shaping Decision Models for Stochastic Dynamic Optimization Problems via Reinforcement Learning","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7159767802","doi":"https://doi.org/10.1002/net.70039"},"language":"en","primary_location":{"id":"doi:10.1002/net.70039","is_oa":true,"landing_page_url":"https://doi.org/10.1002/net.70039","pdf_url":null,"source":{"id":"https://openalex.org/S191798613","display_name":"Networks","issn_l":"0028-3045","issn":["0028-3045","1097-0037"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1002/net.70039","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071445737","display_name":"Florentin D. Hildebrandt","orcid":"https://orcid.org/0000-0003-0298-275X"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florentin D. Hildebrandt","raw_affiliation_strings":["Chair of Management Science Otto\u2010von\u2010Guericke\u2010Universit\u00e4t  Magdeburg Germany"],"raw_orcid":"https://orcid.org/0000-0003-0298-275X","affiliations":[{"raw_affiliation_string":"Chair of Management Science Otto\u2010von\u2010Guericke\u2010Universit\u00e4t  Magdeburg Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029260722","display_name":"Alexander Bode","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Bode","raw_affiliation_strings":["Institute for Decision Support Technische Universit\u00e4t Braunschweig  Braunschweig Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Decision Support Technische Universit\u00e4t Braunschweig  Braunschweig Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135061106","display_name":"Marlin W. Ulmer","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marlin W. Ulmer","raw_affiliation_strings":["Chair of Management Science Otto\u2010von\u2010Guericke\u2010Universit\u00e4t  Magdeburg Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Management Science Otto\u2010von\u2010Guericke\u2010Universit\u00e4t  Magdeburg Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048497223","display_name":"Dirk C. Mattfeld","orcid":"https://orcid.org/0000-0003-1943-838X"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dirk C. Mattfeld","raw_affiliation_strings":["Institute for Decision Support Technische Universit\u00e4t Braunschweig  Braunschweig Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Decision Support Technische Universit\u00e4t Braunschweig  Braunschweig Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":{"value":3400,"currency":"USD","value_usd":3400},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50719471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"88","issue":"1","first_page":"138","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2087000012397766,"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":0.2087000012397766,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.17970000207424164,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.12710000574588776,"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":0.8385000228881836},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7152000069618225},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5432999730110168},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5325000286102295},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.521399974822998},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5016000270843506},{"id":"https://openalex.org/keywords/optimal-decision","display_name":"Optimal decision","score":0.49959999322891235},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4936999976634979},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.48489999771118164},{"id":"https://openalex.org/keywords/dynamic-decision-making","display_name":"Dynamic decision-making","score":0.4431000053882599}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8385000228881836},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7152000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6944000124931335},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6610000133514404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.521399974822998},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C150325174","wikidata":"https://www.wikidata.org/wiki/Q4335500","display_name":"Optimal decision","level":3,"score":0.49959999322891235},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C174988536","wikidata":"https://www.wikidata.org/wiki/Q5318965","display_name":"Dynamic decision-making","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3804999887943268},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C186116695","wikidata":"https://www.wikidata.org/wiki/Q5249226","display_name":"Decision analysis","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.35510000586509705},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C135115379","wikidata":"https://www.wikidata.org/wiki/Q2750514","display_name":"Decision engineering","level":4,"score":0.28540000319480896},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C64431516","wikidata":"https://www.wikidata.org/wiki/Q5249235","display_name":"Decision field theory","level":5,"score":0.27070000767707825},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/net.70039","is_oa":true,"landing_page_url":"https://doi.org/10.1002/net.70039","pdf_url":null,"source":{"id":"https://openalex.org/S191798613","display_name":"Networks","issn_l":"0028-3045","issn":["0028-3045","1097-0037"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Networks","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1002/net.70039","is_oa":true,"landing_page_url":"https://doi.org/10.1002/net.70039","pdf_url":null,"source":{"id":"https://openalex.org/S191798613","display_name":"Networks","issn_l":"0028-3045","issn":["0028-3045","1097-0037"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Networks","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7013515830039978,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2745884788","display_name":"Integration von Maschinellem Lernen in die kombinatorische dynamische Optimierung f\u00fcr urbane Transportdienste","funder_award_id":"510629371","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1586409345","https://openalex.org/W1980175144","https://openalex.org/W1991479893","https://openalex.org/W2007669664","https://openalex.org/W2013055734","https://openalex.org/W2031596957","https://openalex.org/W2056755342","https://openalex.org/W2060322444","https://openalex.org/W2089207315","https://openalex.org/W2091932422","https://openalex.org/W2103098926","https://openalex.org/W2105339579","https://openalex.org/W2108538642","https://openalex.org/W2111753883","https://openalex.org/W2133997119","https://openalex.org/W2139295133","https://openalex.org/W2144161334","https://openalex.org/W2148849245","https://openalex.org/W2152563070","https://openalex.org/W2159615681","https://openalex.org/W2164674071","https://openalex.org/W2257979135","https://openalex.org/W2463987837","https://openalex.org/W2528374652","https://openalex.org/W2550786016","https://openalex.org/W2597664555","https://openalex.org/W2768785583","https://openalex.org/W2794152854","https://openalex.org/W2797064164","https://openalex.org/W2804957066","https://openalex.org/W2898963857","https://openalex.org/W2901816197","https://openalex.org/W2909875311","https://openalex.org/W2911601654","https://openalex.org/W2915653173","https://openalex.org/W2940841755","https://openalex.org/W3002585184","https://openalex.org/W3015302248","https://openalex.org/W3021533098","https://openalex.org/W3035525384","https://openalex.org/W3035829704","https://openalex.org/W3081126571","https://openalex.org/W3109386843","https://openalex.org/W3133544935","https://openalex.org/W3160721969","https://openalex.org/W3174474790","https://openalex.org/W3183225583","https://openalex.org/W3203981070","https://openalex.org/W4214929211","https://openalex.org/W4224232484","https://openalex.org/W4295011616","https://openalex.org/W4306176730","https://openalex.org/W4307104334","https://openalex.org/W4308780247","https://openalex.org/W4313368120","https://openalex.org/W4321189478","https://openalex.org/W4377695412","https://openalex.org/W4385597561","https://openalex.org/W4388473693","https://openalex.org/W4391174803","https://openalex.org/W4405758404","https://openalex.org/W4406102091"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"With":[1],"rising":[2],"customer":[3],"expectations":[4],"and":[5,12,27,54,73,91,139,147,180,238],"increasing":[6],"computational":[7],"potential,":[8],"many":[9],"transport,":[10],"manufacturing,":[11],"production":[13],"operations":[14],"face":[15],"real\u2010time":[16],"decision":[17,50,75,106,125,175],"making":[18],"in":[19,59,109,150,200,217],"stochastic":[20],"dynamic":[21],"environments.":[22],"Decision":[23],"makers":[24],"must":[25],"find":[26],"adapt":[28],"complex":[29,124],"plans":[30],"that":[31],"are":[32,57],"effective":[33,53,179],"now":[34],"but":[35,100,251],"also":[36,252],"flexible":[37,55,181],"with":[38,127],"respect":[39],"to":[40,86,102,117,144,177,234],"future":[41],"developments.":[42],"The":[43,113,165,187],"challenges":[44],"of":[45,63,98,115,122,161,230],"searching":[46],"a":[47,95,104,141,195,208,218],"high\u2010dimensional":[48],"constrained":[49,105],"space":[51,107,126,176],"for":[52,94,146,221],"decisions":[56,99,149,182],"reflected":[58],"the":[60,64,67,70,74,78,89,119,123,162,171,191,202,228,241,248,254],"three":[61],"parts":[62],"Bellman":[65,163,192],"equation:":[66],"reward":[68,172],"function,":[69,72],"value":[71,92,203],"space.":[76],"In":[77],"literature,":[79],"reinforcement":[80],"learning":[81],"(RL)":[82],"has":[83],"shown":[84],"potential":[85],"quickly":[87],"evaluate":[88,148],"reward\u2010":[90],"function":[93,173,204],"limited":[96],"number":[97],"struggles":[101],"search":[103,121,145],"present":[108],"most":[110],"planning":[111],"problems.":[112],"question":[114],"how":[116,240],"combine":[118],"thorough":[120],"RL\u2010evaluation":[128],"techniques":[129],"is":[130,156,205],"still":[131],"open.":[132],"We":[133,211,226],"propose":[134],"two":[135,167],"RL\u2010based":[136],"solution":[137,215],"methods":[138,168,216,232,237],"detail":[140],"third":[142,188],"one":[143,159],"an":[151],"integrated":[152],"manner.":[153],"Each":[154],"method":[155,189],"inspired":[157],"by":[158,207],"component":[160],"equation.":[164],"first":[166],"dynamically":[169],"shape":[170],"or":[174,183],"encourage":[178],"prohibit":[184],"inflexible":[185],"decisions.":[186],"models":[190],"equation":[193],"as":[194],"mixed\u2010integer":[196],"linear":[197],"programming":[198],"formulation":[199],"which":[201],"approximated":[206],"neural":[209],"network.":[210],"compare":[212],"our":[213,231],"proposed":[214],"structured":[219],"analysis":[220],"carefully":[222],"designed":[223],"problem":[224,249],"classes.":[225],"demonstrate":[227],"effectiveness":[229],"compared":[233],"prominent":[235],"benchmark":[236],"highlight":[239],"methods'":[242],"performances":[243],"depend":[244],"not":[245],"only":[246],"on":[247,253],"classes":[250],"instances'":[255],"parameterizations.":[256]},"counts_by_year":[],"updated_date":"2026-06-03T06:16:58.514037","created_date":"2026-05-03T00:00:00"}