{"id":"https://openalex.org/W4414538901","doi":"https://doi.org/10.1109/icc52391.2025.11161534","title":"The Impact of Reinforcement Learning Formulations on Solving the Routing and Spectrum Assignment Problem","display_name":"The Impact of Reinforcement Learning Formulations on Solving the Routing and Spectrum Assignment Problem","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414538901","doi":"https://doi.org/10.1109/icc52391.2025.11161534"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11161534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","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/A5021839275","display_name":"Filippos Christou","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Filippos Christou","raw_affiliation_strings":["Institute of Communication Networks and Computer Engineering (IKR), University of Stuttgart,Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Networks and Computer Engineering (IKR), University of Stuttgart,Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119739793","display_name":"Nicolas Hornek","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicolas Hornek","raw_affiliation_strings":["Institute of Communication Networks and Computer Engineering (IKR), University of Stuttgart,Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Networks and Computer Engineering (IKR), University of Stuttgart,Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031502396","display_name":"Andreas Kirst\u00e4dter","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Kirst\u00e4dter","raw_affiliation_strings":["Institute of Communication Networks and Computer Engineering (IKR), University of Stuttgart,Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Networks and Computer Engineering (IKR), University of Stuttgart,Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32625379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1445","last_page":"1451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.7910000085830688,"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":0.7910000085830688,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8303999900817871},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7182000279426575},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6610999703407288},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6434999704360962},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.5649999976158142},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4749999940395355},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.44029998779296875},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.430400013923645}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8303999900817871},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7182000279426575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830000281333923},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6610999703407288},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6434999704360962},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.61080002784729},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.5649999976158142},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C85044808","wikidata":"https://www.wikidata.org/wiki/Q620614","display_name":"Assignment problem","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C25360446","wikidata":"https://www.wikidata.org/wiki/Q1512771","display_name":"Linear programming relaxation","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2718999981880188}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11161534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1579655362","https://openalex.org/W2069804015","https://openalex.org/W2118404561","https://openalex.org/W2123071102","https://openalex.org/W2315036522","https://openalex.org/W2326998627","https://openalex.org/W2588623852","https://openalex.org/W2616607921","https://openalex.org/W2951309479","https://openalex.org/W2960532465","https://openalex.org/W2973778684","https://openalex.org/W3006432778","https://openalex.org/W3009814504","https://openalex.org/W3088915330","https://openalex.org/W3205392690","https://openalex.org/W3217311638","https://openalex.org/W4285087766","https://openalex.org/W4285210946","https://openalex.org/W4387705273","https://openalex.org/W4388406678"],"related_works":[],"abstract_inverted_index":{"Every":[0],"day,":[1],"an":[2],"increasing":[3],"number":[4],"of":[5,12,129],"services":[6],"rely":[7],"on":[8,98,152],"the":[9,44,100,111,127,144,153,164,177,193,201],"efficient":[10],"operation":[11],"communication":[13],"networks.":[14],"Although":[15],"these":[16,117],"networks":[17,33],"have":[18],"grown":[19],"overly":[20],"complex,":[21],"their":[22,96],"principal":[23],"purpose":[24],"will":[25],"always":[26,104],"remain":[27],"to":[28,67,73,219],"enable":[29],"data":[30,40],"exchange.":[31],"IP-Optical":[32],"play":[34],"a":[35,212],"pivotal":[36],"role":[37],"in":[38,78],"worldwide":[39],"transmission,":[41],"for":[42],"which":[43],"routing":[45],"and":[46,59,76,95,123,143,172,192,208,224],"spectrum":[47],"assignment/allocation":[48],"(RSA)":[49],"problem":[50,102],"must":[51],"be":[52],"solved.":[53],"While":[54],"useful,":[55],"traditional":[56],"optimization":[57,108],"methods":[58],"heuristics":[60],"fall":[61],"short":[62],"under":[63],"certain":[64],"conditions,":[65],"urging":[66],"consider":[68],"reinforcement":[69],"learning":[70],"(RL)":[71],"due":[72],"its":[74],"adaptability":[75],"efficiency":[77],"handling":[79],"complex":[80],"decision-making":[81],"problems.":[82],"This":[83],"paper":[84],"extensively":[85],"analyzes":[86],"various":[87],"partially":[88],"observable":[89],"Markov":[90],"decision":[91],"process":[92],"(POMDP)":[93],"formulations":[94,118,184],"impact":[97],"solving":[99],"RSA":[101],"while":[103],"using":[105,211],"proximal":[106],"policy":[107],"(PPO)":[109],"as":[110,134],"underlying":[112],"RL":[113,130,159,178],"algorithm.":[114],"We":[115],"evaluate":[116],"across":[119,189],"different":[120],"network":[121],"topologies":[122],"demand":[124],"patterns,":[125],"benchmarking":[126],"performance":[128,188],"against":[131],"baselines":[132],"such":[133,207],"k-shortest":[135],"path":[136],"first-fit":[137],"(KSPFF),":[138],"integer":[139],"linear":[140],"programming":[141],"(ILP),":[142],"random":[145],"policy.":[146],"Our":[147],"findings":[148,210],"confirm":[149],"critical":[150],"dependence":[151],"formulation,":[154],"which,":[155],"when":[156],"done":[157],"properly,":[158],"can":[160],"match":[161],"or":[162],"outperform":[163],"baselines.":[165],"Notably,":[166],"POMDPs":[167],"with":[168,216],"fewer":[169],"possible":[170],"actions":[171],"more":[173],"concise":[174],"observations":[175],"improve":[176],"agent's":[179],"performance.":[180,203],"The":[181,204],"best":[182],"POMDP":[183],"also":[185],"exhibit":[186],"consistent":[187],"multiple":[190],"topologies,":[191],"differently":[194],"defined":[195],"reward":[196],"signals":[197],"do":[198],"not":[199],"affect":[200],"overall":[202],"study":[205],"presents":[206],"similar":[209],"carefully":[213],"planned":[214],"workflow":[215],"close":[217],"attention":[218],"statistical":[220],"significance,":[221],"appropriate":[222],"baselines,":[223],"comprehensive":[225],"visualizations.":[226]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}