{"id":"https://openalex.org/W3192766916","doi":"https://doi.org/10.24963/ijcai.2021/357","title":"Reinforcement Learning for Route Optimization with Robustness Guarantees","display_name":"Reinforcement Learning for Route Optimization with Robustness Guarantees","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3192766916","doi":"https://doi.org/10.24963/ijcai.2021/357","mag":"3192766916"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/357","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/357","pdf_url":"https://www.ijcai.org/proceedings/2021/0357.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0357.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084704118","display_name":"Tobias Jacobs","orcid":"https://orcid.org/0000-0002-9165-1161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Jacobs","raw_affiliation_strings":["NEC Laboratories Europe GmBH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories Europe GmBH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088490426","display_name":"Francesco Alesiani","orcid":"https://orcid.org/0000-0003-4413-7247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Alesiani","raw_affiliation_strings":["NEC Laboratories Europe GmBH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories Europe GmBH","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075576380","display_name":"G\u00fcl\u00e7in Ermi\u015f","orcid":"https://orcid.org/0000-0002-6545-6979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gulcin Ermis","raw_affiliation_strings":["NEC Laboratories Europe GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories Europe GmbH","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8737,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.78336703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2592","last_page":"2598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9990000128746033,"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/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9990000128746033,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T12288","display_name":"Optimization and Search Problems","score":0.989300012588501,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8188779950141907},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7356158494949341},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6753714084625244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6687583923339844},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6493165493011475},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.583128035068512},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5490956902503967},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5075539350509644},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.42510873079299927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3442010283470154},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23506757616996765}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8188779950141907},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7356158494949341},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6753714084625244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6687583923339844},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6493165493011475},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.583128035068512},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5490956902503967},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5075539350509644},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.42510873079299927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3442010283470154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23506757616996765},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/357","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/357","pdf_url":"https://www.ijcai.org/proceedings/2021/0357.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/357","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/357","pdf_url":"https://www.ijcai.org/proceedings/2021/0357.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3863150088","display_name":"COGnitive Logistics Operations through secure, dynamic and ad-hoc collaborative networks","funder_award_id":"769141","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3192766916.pdf","grobid_xml":"https://content.openalex.org/works/W3192766916.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1559839959","https://openalex.org/W2006093909","https://openalex.org/W2023964406","https://openalex.org/W2042816232","https://openalex.org/W2118666439","https://openalex.org/W2127331687","https://openalex.org/W2131116400","https://openalex.org/W2145339207","https://openalex.org/W2299115575","https://openalex.org/W2509755532","https://openalex.org/W2602963933","https://openalex.org/W2607264901","https://openalex.org/W2773525213","https://openalex.org/W2805798351","https://openalex.org/W2891879843","https://openalex.org/W2905342215","https://openalex.org/W2912555327","https://openalex.org/W2950191616","https://openalex.org/W3018776722","https://openalex.org/W3035768633","https://openalex.org/W3036460062","https://openalex.org/W3094001213","https://openalex.org/W4287755359","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2794103424","https://openalex.org/W1996530509","https://openalex.org/W3028317537","https://openalex.org/W2389515972","https://openalex.org/W4245435724","https://openalex.org/W2055301889","https://openalex.org/W4400979532","https://openalex.org/W2376554934","https://openalex.org/W2077790809","https://openalex.org/W1505959757"],"abstract_inverted_index":{"Application":[0],"of":[1,17,112,125,173],"deep":[2],"learning":[3],"to":[4,46,64,82,150,161],"NP-hard":[5],"combinatorial":[6],"optimization":[7],"problems":[8],"is":[9,36,45,148,159],"an":[10,80],"emerging":[11],"research":[12],"trend,":[13],"and":[14,60,98,181,192],"a":[15,37,42,66,95,130],"number":[16],"interesting":[18],"approaches":[19],"have":[20],"been":[21],"published":[22],"over":[23,109,129],"the":[24,55,69,76,91,107,110,121,126,143,152,162,177,182,195],"last":[25],"few":[26],"years.":[27],"In":[28],"this":[29,117],"work":[30],"we":[31,157],"address":[32],"robust":[33,51],"optimization,":[34],"which":[35],"more":[38],"complex":[39],"variant":[40],"where":[41,186],"max-min":[43],"problem":[44,58],"be":[47,100,136],"solved.":[48],"We":[49,115,165],"obtain":[50,189],"solutions":[52,104,191],"by":[53,106,119,138,169],"solving":[54,170],"inner":[56,77],"minimization":[57,73],"exactly":[59],"apply":[61],"Reinforcement":[62],"Learning":[63],"learn":[65],"heuristic":[67,141],"for":[68,102,142,176],"outer":[70],"problem.":[71,145],"The":[72,146],"term":[74],"in":[75,94,123],"objective":[78],"represents":[79],"obstacle":[81,118],"existing":[83],"RL-based":[84],"approaches,":[85],"as":[86,156],"its":[87],"value":[88],"depends":[89],"on":[90],"full":[92],"solution":[93],"non-linear":[96],"manner":[97],"cannot":[99],"evaluated":[101],"partial":[103],"constructed":[105],"agent":[108,147],"course":[111],"each":[113],"episode.":[114],"overcome":[116],"defining":[120],"reward":[122],"terms":[124],"one-step":[127],"advantage":[128],"baseline":[131],"policy":[132],"whose":[133],"role":[134],"can":[135],"played":[137],"any":[139],"fast":[140],"given":[144],"trained":[149],"maximize":[151],"total":[153],"advantage,":[154],"which,":[155],"show,":[158],"equivalent":[160],"original":[163],"objective.":[164],"validate":[166],"our":[167,187],"approach":[168],"min-max":[171],"versions":[172],"standard":[174],"benchmarks":[175],"Capacitated":[178],"Vehicle":[179],"Routing":[180],"Traveling":[183],"Salesperson":[184],"Problem,":[185],"agents":[188],"near-optimal":[190],"improve":[193],"upon":[194],"baselines.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}