{"id":"https://openalex.org/W2128161709","doi":"https://doi.org/10.1109/cig.2008.5035652","title":"Hierarchical Nash-Q learning in continuous games","display_name":"Hierarchical Nash-Q learning in continuous games","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2128161709","doi":"https://doi.org/10.1109/cig.2008.5035652","mag":"2128161709"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2008.5035652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2008.5035652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Symposium On Computational Intelligence and Games","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/A5012407311","display_name":"Mostafa Sahraei\u2010Ardakani","orcid":"https://orcid.org/0000-0002-5770-8291"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mostafa Sahraei-Ardakani","raw_affiliation_strings":["CIPCE, ECE Department, College of Engineering, University of Tehran, Tehran, Iran","ECE Dept., Univeristy of Tehran, Tehran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIPCE, ECE Department, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"ECE Dept., Univeristy of Tehran, Tehran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008720205","display_name":"Ashkan Rahimi\u2010Kian","orcid":"https://orcid.org/0000-0001-6814-6119"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ashkan Rahimi-Kian","raw_affiliation_strings":["CIPCE, ECE Department, College of Engineering, University of Tehran, Tehran, Iran","ECE Dept., Univeristy of Tehran, Tehran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIPCE, ECE Department, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"ECE Dept., Univeristy of Tehran, Tehran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049703112","display_name":"Majid Nili-Ahmadabadi","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Majid Nili-Ahmadabadi","raw_affiliation_strings":["CIPCE, ECE Department, College of Engineering, University of Tehran, Tehran, Iran","ECE Dept., Univeristy of Tehran, Tehran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIPCE, ECE Department, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"ECE Dept., Univeristy of Tehran, Tehran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10518303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"290","last_page":"295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11031","display_name":"Game Theory and Applications","score":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.815493106842041},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7560750246047974},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7150120139122009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.651597797870636},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6087285280227661},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.5600200295448303},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5057446956634521},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4733307957649231},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4635806083679199},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34115132689476013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2918507158756256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23075619339942932}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.815493106842041},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7560750246047974},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7150120139122009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.651597797870636},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6087285280227661},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.5600200295448303},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5057446956634521},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4733307957649231},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4635806083679199},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34115132689476013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2918507158756256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23075619339942932},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2008.5035652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2008.5035652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Symposium On Computational Intelligence and Games","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":14,"referenced_works":["https://openalex.org/W806096526","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W2068627087","https://openalex.org/W2080527621","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2156194062","https://openalex.org/W2164637474","https://openalex.org/W4255047891","https://openalex.org/W6630520071","https://openalex.org/W6631168379","https://openalex.org/W6684470913"],"related_works":["https://openalex.org/W2236801283","https://openalex.org/W2728657731","https://openalex.org/W1853631319","https://openalex.org/W2092374696","https://openalex.org/W2481143976","https://openalex.org/W2803932348","https://openalex.org/W3207342620","https://openalex.org/W2607684552","https://openalex.org/W2013767790","https://openalex.org/W4241870466"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"algorithms":[4,94],"usually":[5],"work":[6],"on":[7],"repeated":[8],"extended,":[9],"or":[10],"stochastic":[11],"games.":[12],"Generally":[13],"RL":[14,93],"is":[15,40,43,60,77,90],"developed":[16],"for":[17],"discrete":[18,53],"systems":[19],"both":[20],"in":[21,37,66,86,92],"terms":[22],"of":[23,50,55,70,104],"states":[24],"and":[25,83],"actions.":[26],"In":[27],"this":[28],"paper,":[29],"a":[30,67],"hierarchical":[31,56],"method":[32],"to":[33,45,62,64,79,99],"learn":[34],"equilibrium":[35],"strategy":[36],"continuous":[38,48],"games":[39,71,82],"developed.":[41],"Hierarchy":[42],"used":[44],"break":[46],"the":[47,84],"domain":[49],"strategies":[51],"into":[52],"sets":[54],"strategies.":[57,74],"The":[58],"algorithm":[59],"proved":[61],"converge":[63],"Nash-equilibrium":[65],"specific":[68],"class":[69],"with":[72],"dominant":[73],"Then,":[75],"it":[76],"applied":[78,98],"some":[80],"other":[81],"convergence":[85,105],"shown.":[87],"This":[88],"approach":[89],"common":[91],"that":[95],"they":[96],"are":[97],"problem":[100],"where":[101],"no":[102],"proof":[103],"exits.":[106]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}