{"id":"https://openalex.org/W4402830239","doi":"https://doi.org/10.1109/tcns.2024.3469031","title":"Model-Free Learning and Optimal Policy Design in Multiagent MDPs Under Probabilistic Agent Dropout","display_name":"Model-Free Learning and Optimal Policy Design in Multiagent MDPs Under Probabilistic Agent Dropout","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4402830239","doi":"https://doi.org/10.1109/tcns.2024.3469031"},"language":"en","primary_location":{"id":"doi:10.1109/tcns.2024.3469031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2024.3469031","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","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/A5028041773","display_name":"Carmel Fiscko","orcid":"https://orcid.org/0000-0002-3053-0833"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carmel Fiscko","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","Dept. of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077268766","display_name":"Soummya Kar","orcid":"https://orcid.org/0000-0002-8060-5581"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soummya Kar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","Dept. of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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":["Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, USA","Dept. of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Dept. of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, USA","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/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3415,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66536952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":"1","first_page":"361","last_page":"373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9092000126838684,"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":0.9092000126838684,"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/dropout","display_name":"Dropout (neural networks)","score":0.7829496264457703},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7012180089950562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503562331199646},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4993782043457031},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.46263498067855835},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3842296004295349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3673137426376343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3052245080471039},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11453568935394287}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7829496264457703},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7012180089950562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503562331199646},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4993782043457031},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.46263498067855835},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3842296004295349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3673137426376343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3052245080471039},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11453568935394287}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcns.2024.3469031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2024.3469031","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2917921242","display_name":null,"funder_award_id":"DGE1745016","funder_id":"https://openalex.org/F4562087700","funder_display_name":"National Science Foundation Graduate Research Fellowship Program"}],"funders":[{"id":"https://openalex.org/F4562087700","display_name":"National Science Foundation Graduate Research Fellowship Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1865368880","https://openalex.org/W1918371733","https://openalex.org/W2093172757","https://openalex.org/W2159142421","https://openalex.org/W2170400507","https://openalex.org/W2603752963","https://openalex.org/W2967559388","https://openalex.org/W2991046523","https://openalex.org/W3167586364","https://openalex.org/W3181669971","https://openalex.org/W4224314137","https://openalex.org/W4254547512","https://openalex.org/W4314945926","https://openalex.org/W4318586179","https://openalex.org/W4388469756","https://openalex.org/W4389674424","https://openalex.org/W4402830239","https://openalex.org/W6640490175","https://openalex.org/W6679004901","https://openalex.org/W6689664320","https://openalex.org/W6704084210","https://openalex.org/W6749032143","https://openalex.org/W6762026818","https://openalex.org/W6770752742","https://openalex.org/W6772434598","https://openalex.org/W6774966973","https://openalex.org/W6779771741"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W2782041652","https://openalex.org/W2612657834","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W2952088488","https://openalex.org/W1521968289","https://openalex.org/W4225691210","https://openalex.org/W2481230473","https://openalex.org/W4399568863"],"abstract_inverted_index":{"This":[0,191],"work":[1],"studies":[2],"a":[3,51,62,79,127,160,197,262],"multiagent":[4],"Markov":[5],"decision":[6],"process":[7],"(MDP)":[8],"that":[9,42,72,95,102,112,166,182,203],"can":[10,123,171,185,260],"undergo":[11],"agent":[12,258],"dropout":[13,57,189,208,259,269],"and":[14,26,66,90,100,231,236],"the":[15,20,29,44,47,55,76,84,97,106,116,119,134,145,153,167,178,212,228,244],"computation":[16],"of":[17,28,46,54,83,105,118,144,155,246,257],"policies":[18,184,267],"for":[19,207,226],"postdropout":[21,121,233,266],"system":[22,49,77,122,214,234],"based":[23],"on":[24],"control":[25],"sampling":[27,200],"predropout":[30,179,217],"system.":[31],"The":[32,219],"central":[33],"planner's":[34],"objective":[35],"is":[36,164,193,237,249],"to":[37,136,195],"find":[38,264],"an":[39],"optimal":[40],"policy":[41,198,205,220],"maximizes":[43],"value":[45,117,170,224],"expected":[48,120],"given":[50],"priori":[52],"knowledge":[53],"agents'":[56],"probabilities.":[58],"For":[59],"MDPs":[60],"with":[61,87,174,215,239],"certain":[63],"transition":[64,93],"independence":[65],"reward":[67],"separability":[68],"structure,":[69],"we":[70],"assume":[71],"removing":[73],"agents":[74,86],"from":[75],"forms":[78],"new":[80,88],"MDP":[81,169,230],"comprised":[82],"remaining":[85],"state":[89],"action":[91],"spaces,":[92],"dynamics":[94],"marginalize":[96],"removed":[98,107],"agents,":[99],"rewards":[101],"are":[103],"independent":[104],"agents.":[108,156],"We":[109],"first":[110],"show":[111],"under":[113],"these":[114],"assumptions,":[115],"be":[124,172,186],"represented":[125],"by":[126,177],"single":[128],"MDP;":[129],"this":[130,247],"\u201crobust":[131],"MDP\u201d":[132],"eliminates":[133],"need":[135],"evaluate":[137],"all":[138],"<inline-formula":[139,148],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140,149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[141,150],"notation=\"LaTeX\">$2^{N}$</tex-math></inline-formula>":[142],"realizations":[143,235],"system,":[146,180],"where":[147],"notation=\"LaTeX\">$N$</tex-math></inline-formula>":[151],"denotes":[152],"number":[154],"More":[157],"significantly,":[158],"in":[159,251],"model-free":[161],"context,":[162],"it":[163],"shown":[165],"robust":[168,183,229],"estimated":[173],"samples":[175],"generated":[176],"meaning":[181],"found":[187],"before":[188,268],"occurs.":[190,270],"fact":[192],"used":[194],"propose":[196],"importance":[199],"(IS)":[201],"routine":[202,222],"performs":[204],"evaluation":[206],"scenarios":[209],"while":[210],"controlling":[211],"existing":[213],"good":[216,265],"policies.":[218],"IS":[221],"produces":[223],"estimates":[225],"both":[227],"specific":[232],"justified":[238],"exponential":[240],"confidence":[241],"bounds.":[242],"Finally,":[243],"utility":[245],"approach":[248],"verified":[250],"simulation,":[252],"showing":[253],"how":[254],"structural":[255],"properties":[256],"help":[261],"controller":[263]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}