{"id":"https://openalex.org/W4413392969","doi":"https://doi.org/10.23919/acc63710.2025.11107498","title":"Hierarchical MARL with Stackelberg Games","display_name":"Hierarchical MARL with Stackelberg Games","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413392969","doi":"https://doi.org/10.23919/acc63710.2025.11107498"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107498","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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/A5028041773","display_name":"Carmel Fiscko","orcid":"https://orcid.org/0000-0002-3053-0833"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carmel Fiscko","raw_affiliation_strings":["Cornell University,Dept. of Systems Engineering,Ithaca,NY"],"affiliations":[{"raw_affiliation_string":"Cornell University,Dept. of Systems Engineering,Ithaca,NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445174","display_name":"Haoyu Yin","orcid":"https://orcid.org/0009-0005-1588-9310"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Yin","raw_affiliation_strings":["Washington University,Dept. of Electrical and Systems Engineering,St. Louis,MO"],"affiliations":[{"raw_affiliation_string":"Washington University,Dept. of Electrical and Systems Engineering,St. Louis,MO","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006051783","display_name":"Bruno Sinopoli","orcid":"https://orcid.org/0000-0001-5778-4879"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bruno Sinopoli","raw_affiliation_strings":["Washington University,Dept. of Electrical and Systems Engineering,St. Louis,MO"],"affiliations":[{"raw_affiliation_string":"Washington University,Dept. of Electrical and Systems Engineering,St. Louis,MO","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028041773"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12412017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4115","last_page":"4122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7161999940872192,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7161999940872192,"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/stackelberg-competition","display_name":"Stackelberg competition","score":0.9241876602172852},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.6593828797340393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6034077405929565},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.22858300805091858},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1651616096496582},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14300209283828735}],"concepts":[{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.9241876602172852},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.6593828797340393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6034077405929565},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.22858300805091858},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1651616096496582},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14300209283828735},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107498","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1496590343","https://openalex.org/W1990864994","https://openalex.org/W2010739835","https://openalex.org/W2116327978","https://openalex.org/W2126879264","https://openalex.org/W2402328699","https://openalex.org/W2410251583","https://openalex.org/W2492629073","https://openalex.org/W2798425997","https://openalex.org/W2989068617","https://openalex.org/W2991046523","https://openalex.org/W4315701099","https://openalex.org/W4388430627"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2032294417","https://openalex.org/W2152754392","https://openalex.org/W1989172970"],"abstract_inverted_index":{"We":[0,13,90,152],"consider":[1],"a":[2,9,18,27,44,49,72,99,103,138],"multi-agent":[3,20],"system":[4,16],"under":[5,155],"the":[6,15,34,38,61,77,86,115,130,148,165],"control":[7,36,63],"of":[8],"central":[10],"planner":[11],"(CP).":[12],"model":[14,132],"as":[17],"hierarchical":[19,149],"reinforcement":[21,142],"learning":[22,143],"(MARL)":[23],"problem":[24,95],"in":[25,173],"which":[26,53],"state":[28],"process":[29],"is":[30,68,96,133,171],"influenced":[31],"by":[32],"both":[33],"CP\u2019s":[35,62,66,87],"and":[37,119],"agents\u2019":[39],"actions.":[40],"Each":[41],"agent":[42],"learns":[43],"local":[45,50],"policy":[46,74,83],"to":[47,70,98,110,123,164],"maximize":[48],"value":[51,88],"function,":[52],"may":[54,56],"or":[55],"not":[57],"be":[58,108,121],"aligned":[59],"with":[60],"objective.":[64],"The":[65],"goal":[67],"therefore":[69],"find":[71],"global":[73],"such":[75],"that":[76,84,93,154],"agents":[78],"learn":[79],"an":[80],"equilibrium":[81,118],"joint":[82],"maximizes":[85],"function.":[89],"first":[91],"show":[92],"this":[94,105,159],"equivalent":[97],"Stackelberg":[100,117,167],"game.":[101,168],"Given":[102],"model,":[104],"equivalence":[106],"can":[107,120,161],"used":[109,122],"derive":[111],"game-theoretic":[112],"properties":[113],"about":[114],"desired":[116,166],"solve":[124],"for":[125],"optimal":[126],"policies":[127],"directly.":[128],"If":[129],"game":[131,150],"unknown,":[134],"then":[135],"we":[136],"propose":[137],"Monte":[139],"Carlo":[140],"(MC)-based":[141],"(RL)":[144],"method":[145,160],"based":[146],"on":[147,175],"structure.":[151],"demonstrate":[153],"standard":[156],"RL":[157],"assumptions,":[158],"approximate":[162],"solutions":[163],"This":[169],"procedure":[170],"validated":[172],"simulations":[174],"synthetic":[176],"games":[177],"resembling":[178],"social":[179],"welfare":[180],"problems.":[181]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
