{"id":"https://openalex.org/W4405269769","doi":"https://doi.org/10.1109/tac.2024.3515651","title":"Teaching Coordination to Selfish Learning Agents in Resource-Constrained Partially Observable Markov Games","display_name":"Teaching Coordination to Selfish Learning Agents in Resource-Constrained Partially Observable Markov Games","publication_year":2024,"publication_date":"2024-12-11","ids":{"openalex":"https://openalex.org/W4405269769","doi":"https://doi.org/10.1109/tac.2024.3515651"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3515651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3515651","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-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/A5021157019","display_name":"\u0393\u03b5\u03ce\u03c1\u03b3\u03b9\u03bf\u03c2 \u03a4\u03c3\u03b1\u03bf\u03cd\u03c3\u03bf\u03b3\u03bb\u03bf\u03c5","orcid":"https://orcid.org/0000-0002-8222-7027"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Georgios Tsaousoglou","raw_affiliation_strings":["Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark","Department of Applied Mathematics and Computer Science, Technical University of Denmark, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021157019"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20838075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"70","issue":"5","first_page":"3449","last_page":"3455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.991100013256073,"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":0.991100013256073,"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":0.9821000099182129,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9610000252723694,"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/markov-chain","display_name":"Markov chain","score":0.6145901083946228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.609920859336853},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5888930559158325},{"id":"https://openalex.org/keywords/coordination-game","display_name":"Coordination game","score":0.5487396121025085},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4815081059932709},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.43808454275131226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39237162470817566},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3811658024787903},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3432873487472534},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2720213532447815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2193910777568817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2118607461452484}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6145901083946228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609920859336853},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5888930559158325},{"id":"https://openalex.org/C107257861","wikidata":"https://www.wikidata.org/wiki/Q656316","display_name":"Coordination game","level":2,"score":0.5487396121025085},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4815081059932709},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.43808454275131226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39237162470817566},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3811658024787903},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3432873487472534},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2720213532447815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2193910777568817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2118607461452484},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/tac.2024.3515651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3515651","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W2101786389","https://openalex.org/W2103151730","https://openalex.org/W2116566254","https://openalex.org/W2137906183","https://openalex.org/W2159047277","https://openalex.org/W2171081201","https://openalex.org/W2487793673","https://openalex.org/W2968359733","https://openalex.org/W2991046523","https://openalex.org/W3089603300","https://openalex.org/W3123129857","https://openalex.org/W3165905482"],"related_works":["https://openalex.org/W131709709","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W4236062181","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586"],"abstract_inverted_index":{"Of":[0],"increasing":[1],"relevance":[2],"to":[3,13,30,40,45,50,55,103,107],"engineering":[4],"systems":[5],"are":[6,74],"problems":[7],"that":[8,15,48],"include":[9],"online":[10],"resource":[11,33,44],"allocation":[12,34],"agents":[14,47,91],"feature":[16],"adaptation":[17],"and":[18],"learning":[19,54,90],"capabilities.":[20],"This":[21],"article":[22],"considers":[23],"the":[24,60,64,96,100,108],"case":[25,87],"where":[26],"a":[27,32,37,43,67,77,85],"coordinator":[28],"gets":[29],"design":[31],"mechanism":[35,69],"(i.e.,":[36],"bidding-allocation-rewards":[38],"protocol)":[39],"efficiently":[41],"allocate":[42],"selfish":[46],"try":[49],"gain":[51],"access":[52],"by":[53],"communicate":[56],"strategically.":[57],"Toward":[58],"aligning":[59],"agents'":[61],"incentives":[62],"with":[63,88],"social":[65],"objective,":[66],"critical-value-based":[68],"is":[70],"proposed.":[71],"Analytic":[72],"results":[73,83],"presented":[75],"for":[76,84],"simple,":[78],"stylized":[79],"setting,":[80],"whereas":[81],"simulation":[82],"use":[86],"reinforcement":[89],"controlling":[92],"flexible":[93],"loads":[94],"in":[95],"smart":[97],"grid":[98],"demonstrate":[99],"mechanism's":[101],"ability":[102],"teach":[104],"coordinated":[105],"behavior":[106],"distributed":[109],"learners.":[110]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}