{"id":"https://openalex.org/W3200363463","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533697","title":"Learning 2-opt Local Search from Heuristics as Expert Demonstrations","display_name":"Learning 2-opt Local Search from Heuristics as Expert Demonstrations","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200363463","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533697","mag":"3200363463"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.tue.nl/en/publications/5e31f84a-9702-476e-8411-deffad20e6ad","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035111273","display_name":"Paulo da Costa","orcid":"https://orcid.org/0000-0003-0509-8724"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paulo Da Costa","raw_affiliation_strings":["School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077147157","display_name":"Yingqian Zhang","orcid":"https://orcid.org/0000-0002-5073-0787"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yingqian Zhang","raw_affiliation_strings":["School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067635161","display_name":"Alp Ak\u00e7ay","orcid":"https://orcid.org/0000-0003-2000-6816"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alp Akcay","raw_affiliation_strings":["School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080242338","display_name":"Uzay Kaymak","orcid":"https://orcid.org/0000-0002-4500-9098"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Uzay Kaymak","raw_affiliation_strings":["School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.1362,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.54699487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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/T11182","display_name":"Auction Theory and Applications","score":0.9926999807357788,"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/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9889000058174133,"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/heuristics","display_name":"Heuristics","score":0.8437991142272949},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8403467535972595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7899851202964783},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5651766061782837},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5521581768989563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5501880049705505},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5143926739692688},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46608513593673706},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.464033842086792},{"id":"https://openalex.org/keywords/travelling-salesman-problem","display_name":"Travelling salesman problem","score":0.4618391692638397},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0913625955581665}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8437991142272949},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8403467535972595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899851202964783},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5651766061782837},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5521581768989563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501880049705505},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5143926739692688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46608513593673706},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.464033842086792},{"id":"https://openalex.org/C175859090","wikidata":"https://www.wikidata.org/wiki/Q322212","display_name":"Travelling salesman problem","level":2,"score":0.4618391692638397},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0913625955581665},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire/5e31f84a-9702-476e-8411-deffad20e6ad","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/5e31f84a-9702-476e-8411-deffad20e6ad","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Da Costa, P, Zhang, Y, Akcay, A & Kaymak, U 2021, Learning 2-opt Local Search from Heuristics as Expert Demonstrations. in 2021 International Joint Conference on Neural Networks (IJCNN)., 9533697, Institute of Electrical and Electronics Engineers, 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, 18/07/21. https://doi.org/10.1109/IJCNN52387.2021.9533697","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.tue.nl:publications/5e31f84a-9702-476e-8411-deffad20e6ad","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85116433384&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Da Costa, P, Zhang, Y, Akcay, A & Kaymak, U 2021, Learning 2-opt Local Search from Heuristics as Expert Demonstrations. in 2021 International Joint Conference on Neural Networks (IJCNN)., 9533697, Institute of Electrical and Electronics Engineers, 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, 18/07/21. https://doi.org/10.1109/IJCNN52387.2021.9533697","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:tue:oai:pure.tue.nl:publications/5e31f84a-9702-476e-8411-deffad20e6ad","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/5e31f84a-9702-476e-8411-deffad20e6ad","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire/5e31f84a-9702-476e-8411-deffad20e6ad","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/5e31f84a-9702-476e-8411-deffad20e6ad","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Da Costa, P, Zhang, Y, Akcay, A & Kaymak, U 2021, Learning 2-opt Local Search from Heuristics as Expert Demonstrations. in 2021 International Joint Conference on Neural Networks (IJCNN)., 9533697, Institute of Electrical and Electronics Engineers, 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, 18/07/21. https://doi.org/10.1109/IJCNN52387.2021.9533697","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4454497801","display_name":"Real-time data-driven maintenance logistics","funder_award_id":"628.009.012","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1850531616","https://openalex.org/W1931877416","https://openalex.org/W2016589492","https://openalex.org/W2017708378","https://openalex.org/W2042986967","https://openalex.org/W2054630393","https://openalex.org/W2055569927","https://openalex.org/W2064675550","https://openalex.org/W2099471712","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2130801532","https://openalex.org/W2139059344","https://openalex.org/W2142641780","https://openalex.org/W2153654605","https://openalex.org/W2155027007","https://openalex.org/W2257979135","https://openalex.org/W2285723830","https://openalex.org/W2507756961","https://openalex.org/W2560592986","https://openalex.org/W2563592268","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2804452021","https://openalex.org/W2804930149","https://openalex.org/W2805798351","https://openalex.org/W2805805280","https://openalex.org/W2912555327","https://openalex.org/W2914275007","https://openalex.org/W2944956154","https://openalex.org/W2948268323","https://openalex.org/W2948433391","https://openalex.org/W2951846985","https://openalex.org/W2952332632","https://openalex.org/W2962957031","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2964015378","https://openalex.org/W2964121744","https://openalex.org/W2970706905","https://openalex.org/W2970731410","https://openalex.org/W2996204157","https://openalex.org/W3014847873","https://openalex.org/W3018897351","https://openalex.org/W3047863327","https://openalex.org/W3107359062","https://openalex.org/W4210580908","https://openalex.org/W4214717370","https://openalex.org/W4289292068","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6639056794","https://openalex.org/W6640174482","https://openalex.org/W6679257226","https://openalex.org/W6680724558","https://openalex.org/W6683204974","https://openalex.org/W6718092244","https://openalex.org/W6725207838","https://openalex.org/W6726873649","https://openalex.org/W6730742100","https://openalex.org/W6748645729","https://openalex.org/W6751285671","https://openalex.org/W6752165109","https://openalex.org/W6756151314","https://openalex.org/W6758687306","https://openalex.org/W6762840543","https://openalex.org/W6763777643"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2031913815"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2,120],"(RL)":[3],"has":[4,80],"achieved":[5],"high":[6],"success":[7],"in":[8,157,178],"solving":[9],"routing":[10],"problems.":[11],"However,":[12],"state-of-the-art":[13,188],"deep":[14,189],"RL":[15,190],"approaches":[16],"require":[17],"a":[18,58,123,158],"considerable":[19],"amount":[20],"of":[21,46,99,126,180],"data":[22,65,128,164,174],"before":[23],"they":[24],"reach":[25],"reasonable":[26],"performance.":[27,148],"This":[28],"may":[29],"be":[30],"acceptable":[31],"for":[32,70],"small":[33,124],"problems,":[34],"but":[35],"as":[36],"instances":[37],"grow":[38],"bigger,":[39],"this":[40,54,110],"fact":[41],"severely":[42],"limits":[43],"the":[44,61,71,78,97,100,146],"applicability":[45],"these":[47],"methods":[48],"to":[49,82,91,114,129,142,186],"many":[50],"real-world":[51],"instances.":[52],"In":[53,75,109],"work,":[55],"we":[56,112,134],"study":[57],"setting":[59],"where":[60],"agent":[62,79],"can":[63,95],"access":[64,81],"from":[66,84],"previously":[67],"handcrafted":[68],"heuristics":[69],"Traveling":[72],"Salesman":[73],"Problem.":[74],"our":[76,152],"setting,":[77],"demonstrations":[83,101],"2-opt":[85],"improvement":[86],"policies.":[87],"Our":[88],"goal":[89],"is":[90],"learn":[92,116],"policies":[93,117,156],"that":[94,151],"surpass":[96],"quality":[98],"while":[102],"requiring":[103],"fewer":[104],"samples":[105],"than":[106,165],"pure":[107],"RL.":[108,176],"study,":[111],"propose":[113],"first":[115],"with":[118],"Imitation":[119],"(IL),":[121],"leveraging":[122],"set":[125],"demonstration":[127,173],"accelerate":[130],"policy":[131,137,167],"learning.":[132],"Afterward,":[133],"combine":[135],"on":[136],"and":[138,161],"value":[139],"approximation":[140],"updates":[141],"improve":[143],"performance":[144],"over":[145],"expert's":[147],"We":[149],"show":[150],"method":[153],"learns":[154],"good":[155],"shorter":[159],"time":[160],"using":[162],"less":[163],"classical":[166],"gradient,":[168],"which":[169],"does":[170],"not":[171],"incorporate":[172],"into":[175],"Moreover,":[177],"terms":[179],"solution":[181],"quality,":[182],"it":[183],"performs":[184],"similarly":[185],"other":[187],"approaches.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}