{"id":"https://openalex.org/W2401399634","doi":"https://doi.org/10.1109/icassp.2016.7472542","title":"Learning in constrained stochastic dynamic potential games","display_name":"Learning in constrained stochastic dynamic potential games","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2401399634","doi":"https://doi.org/10.1109/icassp.2016.7472542","mag":"2401399634"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031787043","display_name":"Sergio Valc\u00e1rcel Macua","orcid":"https://orcid.org/0000-0003-4551-5625"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Sergio Valcarcel Macua","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008317106","display_name":"Santiago Zazo","orcid":"https://orcid.org/0000-0001-9073-7927"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Santiago Zazo","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020455236","display_name":"Javier Zazo","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Zazo","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031787043"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":null,"apc_paid":null,"fwci":0.28187688,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81806061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4568","last_page":"4572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9958999752998352,"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8111173510551453},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6900691986083984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6607869863510132},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6359396576881409},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5965536236763},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5798372626304626},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5604880452156067},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5309661626815796},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5069437026977539},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4532405734062195},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.4361025094985962},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3345208764076233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26256051659584045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22391259670257568},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1405024230480194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13541179895401}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8111173510551453},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6900691986083984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607869863510132},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6359396576881409},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5965536236763},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5798372626304626},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5604880452156067},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5309661626815796},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5069437026977539},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4532405734062195},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.4361025094985962},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3345208764076233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26256051659584045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22391259670257568},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1405024230480194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13541179895401},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W314779054","https://openalex.org/W598929452","https://openalex.org/W1531900088","https://openalex.org/W1560700853","https://openalex.org/W1626155273","https://openalex.org/W1675187506","https://openalex.org/W1986935961","https://openalex.org/W2034019401","https://openalex.org/W2046164988","https://openalex.org/W2073384958","https://openalex.org/W2086761918","https://openalex.org/W2098432798","https://openalex.org/W2101539915","https://openalex.org/W2101786389","https://openalex.org/W2106261932","https://openalex.org/W2109102709","https://openalex.org/W2120968583","https://openalex.org/W2121863487","https://openalex.org/W2126685977","https://openalex.org/W2131440997","https://openalex.org/W2151416233","https://openalex.org/W2151544200","https://openalex.org/W2158462832","https://openalex.org/W2170141744","https://openalex.org/W2173165262","https://openalex.org/W2173248099","https://openalex.org/W2263699442","https://openalex.org/W2532646799","https://openalex.org/W2963864421","https://openalex.org/W3022321359","https://openalex.org/W4205326910","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4234534407","https://openalex.org/W4254090244","https://openalex.org/W6633570229","https://openalex.org/W6675894441","https://openalex.org/W6676072908","https://openalex.org/W6678925830","https://openalex.org/W6682064026","https://openalex.org/W6682074005","https://openalex.org/W6684921986","https://openalex.org/W6692574386"],"related_works":["https://openalex.org/W4389475841","https://openalex.org/W1932159282","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W4285537323","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W2117282672","https://openalex.org/W2379312070","https://openalex.org/W4211224558"],"abstract_inverted_index":{"We":[0,25,66],"extend":[1,73],"earlier":[2],"works":[3],"on":[4],"continuous":[5],"potential":[6],"games":[7],"to":[8,37,40,118],"the":[9,35,41,51,58,99,113],"most":[10],"general":[11],"case:":[12],"stochastic":[13,17],"time":[14],"varying":[15],"environment,":[16],"rewards,":[18],"non-reduced":[19],"form":[20],"and":[21,60,72],"constrained":[22,79],"state-action":[23,80],"sets.":[24],"provide":[26],"conditions":[27],"for":[28,76],"a":[29,44,68,92,106],"Markov":[30],"Nash":[31],"equilibrium":[32],"(MNE)":[33],"of":[34,43,53,82],"game":[36],"be":[38],"equivalent":[39],"solution":[42],"single":[45],"control":[46],"problem.":[47],"Then,":[48],"we":[49,90],"address":[50],"problem":[52],"learning":[54,70],"this":[55],"MNE":[56],"when":[57],"reward":[59],"state":[61],"transition":[62],"models":[63],"are":[64,116],"unknown.":[65],"follow":[67],"reinforcement":[69],"approach":[71],"previous":[74],"algorithms":[75],"working":[77],"with":[78,105,112],"subsets":[81],"real":[83],"vector":[84],"spaces.":[85],"As":[86],"an":[87],"application":[88],"example,":[89],"simulate":[91],"network":[93],"flow":[94],"optimization":[95],"model,":[96],"in":[97],"which":[98],"relays":[100],"have":[101],"batteries":[102],"that":[103],"deplete":[104],"random":[107],"factor.":[108],"The":[109],"results":[110],"obtained":[111],"proposed":[114],"framework":[115],"close":[117],"optimal.":[119]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}