{"id":"https://openalex.org/W7170236310","doi":null,"title":"LaGCO-RL: Reinforcement Learning in Latent Action Spaces for Graph Combinatorial Optimization","display_name":"LaGCO-RL: Reinforcement Learning in Latent Action Spaces for Graph Combinatorial Optimization","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7170236310"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-05671095v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05671095v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2026","raw_type":"Software"},"volume":null,"type":"software","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05671095v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093312122","display_name":"Franco Terranova","orcid":"https://orcid.org/0009-0001-6989-2655","observed_orcids":["https://orcid.org/0009-0001-6989-2655"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4405258536","display_name":"RESIST: R\u00e9silience et \u00e9lasticit\u00e9 pour la mise \u00e0 l'\u00e9chelle et la s\u00e9curit\u00e9 des syst\u00e8mes en r\u00e9seaux dynamiques","ror":"https://ror.org/00vk6my81","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210127166","https://openalex.org/I4210159245","https://openalex.org/I4405258536","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Terranova, Franco","raw_affiliation_strings":["Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex - France)","LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications (Campus Scientifique BP 239 54506 Vandoeuvre-l\u00e8s-Nancy Cedex - France)","RESIST - Resilience and Elasticity for Security and ScalabiliTy of dynamic networked systems (615 rue du Jardin Botanique 54600 Villers-l\u00e8s-Nancy - France)","UL - Universit\u00e9 de Lorraine (34 cours L\u00e9opold - CS 25233 - 54052 Nancy cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex - France)","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications (Campus Scientifique BP 239 54506 Vandoeuvre-l\u00e8s-Nancy Cedex - France)","institution_ids":["https://openalex.org/I4210121838"]},{"raw_affiliation_string":"RESIST - Resilience and Elasticity for Security and ScalabiliTy of dynamic networked systems (615 rue du Jardin Botanique 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I4405258536"]},{"raw_affiliation_string":"UL - Universit\u00e9 de Lorraine (34 cours L\u00e9opold - CS 25233 - 54052 Nancy cedex - France)","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030576977","display_name":"Guillermo Bern\u00e1rdez","orcid":"https://orcid.org/0000-0002-6790-4878","observed_orcids":["https://orcid.org/0000-0002-6790-4878"]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernardez, Guillermo","raw_affiliation_strings":["UC Santa Barbara - UCSB - University of California [Santa Barbara] (Santa Barbara, CA 93106 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Santa Barbara - UCSB - University of California [Santa Barbara] (Santa Barbara, CA 93106 - United States)","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091745795","display_name":"Albert Cabellos\u2010Aparicio","orcid":"https://orcid.org/0000-0001-9329-7584","observed_orcids":["https://orcid.org/0000-0001-9329-7584"]},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Cabellos-Aparicio, Albert","raw_affiliation_strings":["UPC - Universitat Polit\u00e8cnica de Catalunya =  Universit\u00e9 polytechnique de Catalogne = Polytechnic University of Catalunya [Barcelona] (C./Jordi Girona, 1-3, 08034 Barcelona - Spain)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UPC - Universitat Polit\u00e8cnica de Catalunya =  Universit\u00e9 polytechnique de Catalogne = Polytechnic University of Catalunya [Barcelona] (C./Jordi Girona, 1-3, 08034 Barcelona - Spain)","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083733004","display_name":"Nina Miolane","orcid":"https://orcid.org/0000-0002-1200-9024","observed_orcids":["https://orcid.org/0000-0002-1200-9024"]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miolane, Nina","raw_affiliation_strings":["UC Santa Barbara - UCSB - University of California [Santa Barbara] (Santa Barbara, CA 93106 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Santa Barbara - UCSB - University of California [Santa Barbara] (Santa Barbara, CA 93106 - United States)","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111932337","display_name":"Abdelkader Lahmadi","orcid":"https://orcid.org/0000-0003-3882-1560","observed_orcids":["https://orcid.org/0000-0003-3882-1560"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4405258536","display_name":"RESIST: R\u00e9silience et \u00e9lasticit\u00e9 pour la mise \u00e0 l'\u00e9chelle et la s\u00e9curit\u00e9 des syst\u00e8mes en r\u00e9seaux dynamiques","ror":"https://ror.org/00vk6my81","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210127166","https://openalex.org/I4210159245","https://openalex.org/I4405258536","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lahmadi, Abdelkader","raw_affiliation_strings":["Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex - France)","LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications (Campus Scientifique BP 239 54506 Vandoeuvre-l\u00e8s-Nancy Cedex - France)","RESIST - Resilience and Elasticity for Security and ScalabiliTy of dynamic networked systems (615 rue du Jardin Botanique 54600 Villers-l\u00e8s-Nancy - France)","UL - Universit\u00e9 de Lorraine (34 cours L\u00e9opold - CS 25233 - 54052 Nancy cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex - France)","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications (Campus Scientifique BP 239 54506 Vandoeuvre-l\u00e8s-Nancy Cedex - France)","institution_ids":["https://openalex.org/I4210121838"]},{"raw_affiliation_string":"RESIST - Resilience and Elasticity for Security and ScalabiliTy of dynamic networked systems (615 rue du Jardin Botanique 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I4405258536"]},{"raw_affiliation_string":"UL - Universit\u00e9 de Lorraine (34 cours L\u00e9opold - CS 25233 - 54052 Nancy cedex - France)","institution_ids":["https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8920999765396118,"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":0.8920999765396118,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.02930000051856041,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.016100000590085983,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.777999997138977},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7699999809265137},{"id":"https://openalex.org/keywords/combinatorial-optimization","display_name":"combinatorial optimization","score":0.6930000185966492}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105999708175659},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5006999969482422},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C52692508","wikidata":"https://www.wikidata.org/wiki/Q1333872","display_name":"Combinatorial optimization","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4154999852180481},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40720000863075256},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-05671095v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05671095v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2026","raw_type":"Software"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05671095v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05671095v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2026","raw_type":"Software"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161753993","https://openalex.org/W4294610442","https://openalex.org/W3132783035","https://openalex.org/W2998327136","https://openalex.org/W4412877155","https://openalex.org/W4394710865","https://openalex.org/W4390833107","https://openalex.org/W4394653085","https://openalex.org/W4309651818","https://openalex.org/W7114787280"],"abstract_inverted_index":{"LaGCO-RL":[0,74,97],"is":[1,75],"a":[2,36],"modular":[3],"library":[4],"that":[5],"automates":[6],"the":[7,65,80,89,114],"construction":[8],"of":[9,39,82,100],"latent":[10,16],"action":[11],"spaces":[12,18],"and":[13,57,92,113],"semantically":[14],"aligned":[15],"observation":[17],"for":[19,104],"reinforcement":[20],"learning":[21],"(RL)":[22],"in":[23,70,119],"graph-based":[24],"combinatorial":[25],"optimization":[26,84],"(GCO)":[27],"through":[28],"graph":[29],"neural":[30],"network":[31],"(GNN)":[32],"embeddings.The":[33],"framework":[34],"supports":[35],"diverse":[37],"set":[38],"GCO":[40,72],"benchmark":[41],"problems,":[42],"ranging":[43],"from":[44],"tasks":[45,85],"with":[46],"linear":[47],"node":[48],"decision":[49,59],"variables":[50],"to":[51],"more":[52],"realistic":[53],"scenarios":[54],"involving":[55],"structured":[56],"super-linear":[58],"variables.":[60],"This":[61],"broad":[62],"applicability":[63],"addresses":[64],"action-space":[66],"complexity":[67],"gap":[68],"present":[69],"existing":[71],"benchmarks.":[73],"also":[76],"easily":[77],"extensible,":[78],"enabling":[79],"integration":[81],"new":[83],"by":[86],"defining":[87],"only":[88],"environment":[90],"dynamics":[91],"feature":[93],"extraction":[94],"pipeline.In":[95],"addition,":[96],"provides":[98],"implementations":[99],"multiple":[101],"RL-based":[102],"approaches":[103],"GCO,":[105],"including":[106],"standard":[107],"discrete-action":[108],"methods,":[109],"iterative":[110],"Q-learning":[111],"agents,":[112],"projection-based":[115],"RL":[116],"agent":[117],"proposed":[118],"this":[120],"work.":[121]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-07-24T00:00:00"}
