{"id":"https://openalex.org/W4390481262","doi":"https://doi.org/10.1109/iccma59762.2023.10374802","title":"Competitive Reinforcement Learning Agents with Adaptive Networks","display_name":"Competitive Reinforcement Learning Agents with Adaptive Networks","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W4390481262","doi":"https://doi.org/10.1109/iccma59762.2023.10374802"},"language":"en","primary_location":{"id":"doi:10.1109/iccma59762.2023.10374802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccma59762.2023.10374802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 11th International Conference on Control, Mechatronics and Automation (ICCMA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5093630754","display_name":"Herman Pareli Nordaunet","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Herman Pareli Nordaunet","raw_affiliation_strings":["University of Oslo,Department of Informatics,Oslo,Norway","Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103939209","display_name":"T. Hellem Bo","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Trym B\u00f8","raw_affiliation_strings":["University of Oslo,Department of Informatics,Oslo,Norway","Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093630755","display_name":"Evan J\u00e5sund Kassab","orcid":"https://orcid.org/0009-0009-1618-5744"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Evan J\u00e5sund Kassab","raw_affiliation_strings":["University of Oslo,Department of Informatics,Oslo,Norway","Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011724776","display_name":"Frank Veenstra","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Frank Veenstra","raw_affiliation_strings":["University of Oslo,Department of Informatics,Oslo,Norway","Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005034364","display_name":"Ulysse C\u00f4t\u00e9\u2010Allard","orcid":"https://orcid.org/0000-0003-3241-8404"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ulysse C\u00f4t\u00e9-Allard","raw_affiliation_strings":["University of Oslo,Department of Informatics,Oslo,Norway","Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo,Department of Informatics,Oslo,Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"314","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9932000041007996,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8455297946929932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7920489311218262},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6425660848617554},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6295833587646484},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5781644582748413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5769803524017334},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5685608386993408},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.5532193779945374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.494886577129364},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10375523567199707}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8455297946929932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920489311218262},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6425660848617554},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6295833587646484},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5781644582748413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5769803524017334},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5685608386993408},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.5532193779945374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.494886577129364},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10375523567199707},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccma59762.2023.10374802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccma59762.2023.10374802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 11th International Conference on Control, Mechatronics and Automation (ICCMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2310278697","display_name":null,"funder_award_id":"309869","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1565746575","https://openalex.org/W2119144962","https://openalex.org/W2194775991","https://openalex.org/W2608347258","https://openalex.org/W2889987506","https://openalex.org/W2915117209","https://openalex.org/W2944892105","https://openalex.org/W2964233199","https://openalex.org/W2965976751","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2998218113","https://openalex.org/W3007947150","https://openalex.org/W3019321633","https://openalex.org/W3102775700","https://openalex.org/W4220731687","https://openalex.org/W4246193833","https://openalex.org/W4287865629","https://openalex.org/W4298857966","https://openalex.org/W6633774736","https://openalex.org/W6637967152","https://openalex.org/W6677580257","https://openalex.org/W6741753902","https://openalex.org/W6753526802","https://openalex.org/W6762284573","https://openalex.org/W6772005887","https://openalex.org/W6773555910"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"The":[0,148],"depth":[1],"of":[2,28,51,84,93,103,187],"a":[3,8,96,144],"neural":[4],"network's":[5],"architecture":[6],"is":[7,117,124,132,141],"crucial":[9],"decision":[10],"that":[11,98,151],"must":[12],"balance":[13],"network":[14,59,116,123,178],"performance":[15,140,171],"and":[16,23,106,137],"the":[17,26,38,45,49,52,58,62,75,82,114,121,130,138,174,184],"computational":[18,77,161],"resources":[19],"required":[20],"during":[21],"training":[22,100],"inference.":[24],"In":[25],"context":[27],"Reinforcement":[29],"Learning":[30],"(RL),":[31],"this":[32,88],"architectural":[33],"choice":[34],"can":[35],"profoundly":[36],"impact":[37],"policy":[39,131],"(i.e.":[40],"agent's":[41,63],"behavior)":[42],"learned":[43,56,133],"by":[44,57],"network.":[46],"Depending":[47],"on":[48],"state":[50],"agent,":[53],"different":[54,104,156],"policies":[55],"may":[60],"improve":[61],"performance,":[64],"particularly":[65],"for":[66],"time-sensitive":[67],"applications":[68],"(e.g.":[69],"real-time,":[70],"low-latency":[71],"scenarios)":[72],"when":[73],"considering":[74],"additional":[76],"time":[78],"needed":[79],"to":[80,109],"access":[81],"output":[83],"deeper":[85],"networks.":[86],"Therefore,":[87],"paper":[89],"proposes":[90],"Greater":[91],"Use":[92],"Time":[94],"(GUT),":[95],"method":[97],"involves":[99],"multiple":[101,153],"networks":[102,154],"lengths":[105,157],"allowing":[107],"them":[108],"make":[110],"decisions":[111],"collab-oratively.":[112],"If":[113],"shorter":[115],"not":[118,158],"confident":[119],"enough,":[120],"longer":[122],"relied":[125],"on.":[126],"For":[127],"each":[128],"network,":[129],"through":[134],"deep":[135],"Q-learning,":[136],"method's":[139],"evaluated":[142],"in":[143],"competitive":[145],"multi-agent":[146],"environment.":[147],"results":[149],"demonstrate":[150],"using":[152],"with":[155],"only":[159],"reduces":[160],"cost":[162],"at":[163],"inference":[164],"time,":[165],"but":[166],"also":[167,190],"yields":[168],"significantly":[169,191],"better":[170],"than":[172],"either":[173],"short":[175],"or":[176],"long":[177],"alone":[179],"(p":[180,195],"<":[181,196],"0.05).":[182,197],"Importantly,":[183],"proposed":[185],"use":[186],"confidence-based":[188],"decision-making":[189,194],"outperforms":[192],"random":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}