{"id":"https://openalex.org/W3201713031","doi":"https://doi.org/10.1109/ssci50451.2021.9659970","title":"Improving Generalization of Deep Reinforcement Learning-based TSP Solvers","display_name":"Improving Generalization of Deep Reinforcement Learning-based TSP Solvers","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W3201713031","doi":"https://doi.org/10.1109/ssci50451.2021.9659970","mag":"3201713031"},"language":"en","primary_location":{"id":"doi:10.1109/ssci50451.2021.9659970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9659970","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5113528019","display_name":"Wenbin Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Wenbin Ouyang","raw_affiliation_strings":["UM-SJTU Joint Institute, Shanghai Jiao Tong University","University of Michigan"],"affiliations":[{"raw_affiliation_string":"UM-SJTU Joint Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101431030","display_name":"Yisen Wang","orcid":"https://orcid.org/0000-0002-0181-2137"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yisen Wang","raw_affiliation_strings":["UM-SJTU Joint Institute, Shanghai Jiao Tong University","University of Michigan"],"affiliations":[{"raw_affiliation_string":"UM-SJTU Joint Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083429575","display_name":"Shaochen Han","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaochen Han","raw_affiliation_strings":["UM-SJTU Joint Institute, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"UM-SJTU Joint Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017331406","display_name":"Zhejian Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhejian Jin","raw_affiliation_strings":["UM-SJTU Joint Institute, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"UM-SJTU Joint Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073106112","display_name":"Paul Weng","orcid":"https://orcid.org/0000-0002-2008-4569"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Paul Weng","raw_affiliation_strings":["UM-SJTU Joint Institute, Shanghai Jiao Tong University","Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"UM-SJTU Joint Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113528019"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":1.1418,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81715659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9861999750137329,"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/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9835000038146973,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.816292405128479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7435242533683777},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.669469952583313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.595773458480835},{"id":"https://openalex.org/keywords/magic","display_name":"MAGIC (telescope)","score":0.5489974617958069},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5037621855735779},{"id":"https://openalex.org/keywords/travelling-salesman-problem","display_name":"Travelling salesman problem","score":0.4951530992984772},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4353877902030945},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41028502583503723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3750300705432892},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3431471884250641},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31894344091415405},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22327351570129395},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13918304443359375}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.816292405128479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435242533683777},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.669469952583313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595773458480835},{"id":"https://openalex.org/C2777704519","wikidata":"https://www.wikidata.org/wiki/Q45732","display_name":"MAGIC (telescope)","level":2,"score":0.5489974617958069},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5037621855735779},{"id":"https://openalex.org/C175859090","wikidata":"https://www.wikidata.org/wiki/Q322212","display_name":"Travelling salesman problem","level":2,"score":0.4951530992984772},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4353877902030945},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41028502583503723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3750300705432892},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3431471884250641},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31894344091415405},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22327351570129395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13918304443359375},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci50451.2021.9659970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9659970","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2737788528","display_name":null,"funder_award_id":"IPP21141","funder_id":"https://openalex.org/F4320322999","funder_display_name":"Shanghai Jiao Tong University"},{"id":"https://openalex.org/G3130598502","display_name":null,"funder_award_id":"19ZR1426700","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5010798040","display_name":null,"funder_award_id":"61872238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1714211023","https://openalex.org/W2055569927","https://openalex.org/W2064675550","https://openalex.org/W2106371135","https://openalex.org/W2119717200","https://openalex.org/W2133564696","https://openalex.org/W2507756961","https://openalex.org/W2607264901","https://openalex.org/W2805516822","https://openalex.org/W2805798351","https://openalex.org/W2810799211","https://openalex.org/W2912555327","https://openalex.org/W2948433391","https://openalex.org/W2951846985","https://openalex.org/W2952332632","https://openalex.org/W2963084599","https://openalex.org/W2963403868","https://openalex.org/W2964308564","https://openalex.org/W2980930344","https://openalex.org/W2987288550","https://openalex.org/W3014847873","https://openalex.org/W3107359062","https://openalex.org/W3115357289","https://openalex.org/W3123742938","https://openalex.org/W3129625903","https://openalex.org/W3177337956","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6725207838","https://openalex.org/W6730742100","https://openalex.org/W6736495275","https://openalex.org/W6739901393","https://openalex.org/W6763838503","https://openalex.org/W6769524888","https://openalex.org/W6769975600","https://openalex.org/W6787360482","https://openalex.org/W6941249815"],"related_works":["https://openalex.org/W1525389557","https://openalex.org/W2361554335","https://openalex.org/W2164188042","https://openalex.org/W2359992618","https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W4306878646","https://openalex.org/W2054495636","https://openalex.org/W2031913815"],"abstract_inverted_index":{"Recent":[0],"work":[1],"applying":[2],"deep":[3,50],"reinforcement":[4],"learning":[5,51],"(DRL)":[6],"to":[7,34,126],"solve":[8],"traveling":[9],"salesman":[10],"problems":[11],"(TSP)":[12],"has":[13],"shown":[14],"that":[15,47,77,122],"DRL-based":[16,128],"solvers":[17],"can":[18],"be":[19],"fast":[20],"and":[21,53,69,112,139,149,157],"competitive":[22],"with":[23,96],"TSP":[24,81,132,147],"heuristics":[25,148],"for":[26],"small":[27],"instances,":[28,133],"but":[29],"do":[30],"not":[31],"generalize":[32],"well":[33],"larger":[35],"instances.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,90,106,114,119],"propose":[41],"a":[42,49,54,62,65,74,80,100,108],"novel":[43,109],"approach":[44,152],"named":[45],"MAGIC":[46,123],"includes":[48,86],"architecture":[52],"DRL":[55,92],"training":[56,84],"method.":[57],"Our":[58,83],"architecture,":[59],"which":[60],"integrates":[61],"multilayer":[63],"perceptron,":[64],"graph":[66],"neural":[67],"network,":[68],"an":[70],"attention":[71],"model,":[72],"defines":[73],"stochastic":[75],"policy":[76,93],"sequentially":[78],"generates":[79],"solution.":[82],"method":[85,143],"several":[87],"innovations:":[88],"(1)":[89],"interleave":[91],"gradient":[94],"updates":[95],"local":[97,102],"search":[98,103],"(using":[99],"new":[101],"technique),":[104],"(2)":[105],"use":[107],"simple":[110],"baseline,":[111],"(3)":[113],"apply":[115],"curriculum":[116],"learning.":[117],"Finally,":[118],"empirically":[120],"demonstrate":[121],"is":[124],"superior":[125],"other":[127,150],"methods":[129],"on":[130],"random":[131],"both":[134],"in":[135,153],"terms":[136,154],"of":[137,155],"performance":[138,156],"generalizability.":[140],"Moreover,":[141],"our":[142],"compares":[144],"favorably":[145],"against":[146],"state-of-the-art":[151],"computational":[158],"time.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}