{"id":"https://openalex.org/W4315488661","doi":"https://doi.org/10.1109/cdc51059.2022.9992762","title":"Multi-Agent Learning via Markov Potential Games in Marketplaces for Distributed Energy Resources","display_name":"Multi-Agent Learning via Markov Potential Games in Marketplaces for Distributed Energy Resources","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315488661","doi":"https://doi.org/10.1109/cdc51059.2022.9992762"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992762","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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/A5010452533","display_name":"Dheeraj Narasimha","orcid":"https://orcid.org/0000-0002-4489-8217"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dheeraj Narasimha","raw_affiliation_strings":["3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas"],"affiliations":[{"raw_affiliation_string":"3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059675938","display_name":"Kiyeob Lee","orcid":"https://orcid.org/0000-0002-2851-0737"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiyeob Lee","raw_affiliation_strings":["3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas"],"affiliations":[{"raw_affiliation_string":"3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053096993","display_name":"Dileep Kalathil","orcid":"https://orcid.org/0000-0001-7968-5185"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dileep Kalathil","raw_affiliation_strings":["3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas"],"affiliations":[{"raw_affiliation_string":"3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005504863","display_name":"Srinivas Shakkottai","orcid":"https://orcid.org/0000-0002-5882-6433"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Shakkottai","raw_affiliation_strings":["3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas"],"affiliations":[{"raw_affiliation_string":"3128 Texas A&M University,Dept.of Electrical and Computer Engineering,College Station,Texas","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010452533"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":2.5779,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91887997,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6350","last_page":"6357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894999861717224,"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-decision-process","display_name":"Markov decision process","score":0.8021761178970337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7490465044975281},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6940886378288269},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.600518524646759},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5992444753646851},{"id":"https://openalex.org/keywords/potential-game","display_name":"Potential game","score":0.5755159854888916},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5493167042732239},{"id":"https://openalex.org/keywords/demand-response","display_name":"Demand response","score":0.5447285175323486},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5387611389160156},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5179488062858582},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.45578378438949585},{"id":"https://openalex.org/keywords/electricity","display_name":"Electricity","score":0.4437630772590637},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4396921396255493},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4243905544281006},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.423493891954422},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4225504994392395},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4186892509460449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22553518414497375},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.17388483881950378},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11818307638168335},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09567725658416748}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8021761178970337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490465044975281},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6940886378288269},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.600518524646759},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5992444753646851},{"id":"https://openalex.org/C2778079155","wikidata":"https://www.wikidata.org/wiki/Q288500","display_name":"Potential game","level":3,"score":0.5755159854888916},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5493167042732239},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.5447285175323486},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5387611389160156},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5179488062858582},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.45578378438949585},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.4437630772590637},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4396921396255493},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4243905544281006},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.423493891954422},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4225504994392395},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4186892509460449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22553518414497375},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.17388483881950378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11818307638168335},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09567725658416748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992762","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1496590343","https://openalex.org/W1513468570","https://openalex.org/W1542941925","https://openalex.org/W1583837637","https://openalex.org/W1907356258","https://openalex.org/W1971988921","https://openalex.org/W1972768959","https://openalex.org/W2131305292","https://openalex.org/W2162720111","https://openalex.org/W2164601540","https://openalex.org/W2169077434","https://openalex.org/W2273724401","https://openalex.org/W2334899171","https://openalex.org/W2612690371","https://openalex.org/W2615459836","https://openalex.org/W2752505153","https://openalex.org/W2974174348","https://openalex.org/W3022321359","https://openalex.org/W3107615218","https://openalex.org/W3172288035","https://openalex.org/W4206624559","https://openalex.org/W4254547512","https://openalex.org/W4286898817","https://openalex.org/W6630520071","https://openalex.org/W6632657563","https://openalex.org/W6773637655","https://openalex.org/W6786364697","https://openalex.org/W6791976426","https://openalex.org/W6796527454","https://openalex.org/W6797200228","https://openalex.org/W6802197776"],"related_works":["https://openalex.org/W1935632502","https://openalex.org/W4300514062","https://openalex.org/W2955291419","https://openalex.org/W2949715110","https://openalex.org/W2080682057","https://openalex.org/W2949401733","https://openalex.org/W4298859366","https://openalex.org/W2618299181","https://openalex.org/W4214835929","https://openalex.org/W2172106845"],"abstract_inverted_index":{"Much":[0],"change":[1,85],"is":[2,114,119,133,138],"happening":[3],"in":[4,81,86,95,110,148,170,178,192,210,245],"electricity":[5,247],"markets":[6,60],"due":[7],"to":[8,29,38,141,242],"the":[9,51,87,160,167,171,175,198,238,252,255],"entrance":[10],"of":[11,44,89,254],"small-scale":[12],"prosumers":[13],"that":[14,82,136,156,164,186,222],"both":[15,96],"generate":[16],"and":[17,22,57,100,249],"consume":[18],"electricity.":[19],"Both":[20],"large":[21],"small":[23],"consumers":[24],"can":[25,53,64,189,206],"also":[26,203,207],"be":[27,54,190,208],"incentivized":[28],"reduce":[30],"their":[31],"demand":[32],"during":[33],"peak":[34],"load":[35],"periods,":[36],"referred":[37],"as":[39,159],"demand-response.":[40],"The":[41],"net":[42],"effect":[43],"such":[45,62,73],"distributed":[46],"energy":[47],"resources":[48],"(DERs)":[49],"on":[50],"grid":[52],"quite":[55],"substantial,":[56],"designing":[58],"secondary":[59],"wherein":[61,237],"DERs":[63],"participate":[65],"repeatedly":[66],"over":[67],"time":[68],"has":[69],"become":[70],"important.":[71],"Many":[72],"marketplaces":[74],"have":[75],"a":[76,83,101,107,115,153,179,193,211,226],"so-called":[77],"potential":[78,103,116,161,168,199],"game":[79,173],"structure,":[80],"unilateral":[84],"strategy":[88],"an":[90,187,246],"agent":[91],"causes":[92],"equivalent":[93],"changes":[94],"its":[97],"own":[98],"reward":[99],"global":[102],"function.":[104,201],"We":[105,151,183,202],"consider":[106],"dynamic":[108],"setting":[109],"which":[111,125],"each":[112],"stage":[113,172],"game,":[117],"but":[118],"accompanied":[120],"by":[121,196],"Markovian":[122],"state":[123],"transitions,":[124],"we":[126,157,233],"call":[127],"Markov":[128,149,180],"Potential":[129],"Games":[130],"(MPG).":[131],"It":[132],"well":[134],"known":[135],"it":[137],"formidably":[139],"challenging":[140],"compute":[142],"or":[143],"learn":[144],"Nash":[145],"Equilibria":[146],"(NE)":[147],"Games.":[150],"develop":[152],"key":[154],"concept":[155],"term":[158],"value":[162,176,200],"function":[163,169,177],"ties":[165],"together":[166],"with":[174,225],"Decision":[181],"Process.":[182],"first":[184],"show":[185,204,234],"NE":[188,205],"computed":[191],"centralized":[194],"manner":[195,213],"maximizing":[197],"obtained":[209],"multi-agent":[212,228],"via":[214],"asynchronous":[215],"better":[216],"(not":[217],"necessarily":[218],"best)":[219],"response":[220],"updates":[221],"are":[223],"consistent":[224],"simple":[227],"reinforcement":[229],"learning":[230],"algorithm.":[231],"Finally,":[232],"several":[235],"examples":[236],"MPG":[239],"framework":[240],"applies":[241],"DER":[243],"dynamics":[244],"marketplace,":[248],"numerically":[250],"study":[251],"efficiency":[253],"equilibria":[256],"attained.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}