{"id":"https://openalex.org/W2061016179","doi":"https://doi.org/10.1109/cdc.2014.7040086","title":"Blackwell's approachability in stackelberg stochastic games: A learning version","display_name":"Blackwell's approachability in stackelberg stochastic games: A learning version","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2061016179","doi":"https://doi.org/10.1109/cdc.2014.7040086","mag":"2061016179"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2014.7040086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7040086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","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/A5020319328","display_name":"Dileep Kalathi","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dileep Kalathi","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, US","Department of Electrical Engg., University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, US","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Electrical Engg., University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vivek S. Borkar","raw_affiliation_strings":["Department of Electrical Engineering, IIT, Bombay, India","Department of Electrical Engineering, IIT Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, IIT, Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Department of Electrical Engineering, IIT Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002082998","display_name":"Rahul Jain","orcid":"https://orcid.org/0000-0003-3786-8682"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Jain","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA","Department of Electrical Engg., University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Electrical Engg., University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020319328"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74301734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"4467","last_page":"4472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9950000047683716,"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":0.9950000047683716,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9750999808311462,"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/stackelberg-competition","display_name":"Stackelberg competition","score":0.7573023438453674},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6076499819755554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5800284743309021},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5633580088615417},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5429790019989014},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.503140389919281},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4564440846443176},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45485615730285645},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4291204810142517},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3917919993400574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2792590260505676},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.2655959725379944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2279251515865326},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.10244253277778625}],"concepts":[{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.7573023438453674},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6076499819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5800284743309021},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5633580088615417},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5429790019989014},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.503140389919281},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4564440846443176},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45485615730285645},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4291204810142517},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3917919993400574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2792590260505676},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2655959725379944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2279251515865326},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.10244253277778625},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2014.7040086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7040086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W40837621","https://openalex.org/W594357522","https://openalex.org/W1606531263","https://openalex.org/W1982813377","https://openalex.org/W2023026122","https://openalex.org/W2036737894","https://openalex.org/W2099310213","https://openalex.org/W2117626647","https://openalex.org/W2154204727","https://openalex.org/W2168565265","https://openalex.org/W6601654609","https://openalex.org/W6635991037"],"related_works":["https://openalex.org/W2892779699","https://openalex.org/W2097407159","https://openalex.org/W2773557284","https://openalex.org/W2971598508","https://openalex.org/W3014705755","https://openalex.org/W4299507917","https://openalex.org/W3122101132","https://openalex.org/W1573523779","https://openalex.org/W3123657508","https://openalex.org/W2888150550"],"abstract_inverted_index":{"The":[0,17],"notion":[1],"of":[2,13,33,43,46],"approachability":[3,20,69,128],"was":[4],"introduced":[5],"by":[6,54],"Blackwell":[7],"(Blackwell,":[8],"1956)":[9],"in":[10,62],"the":[11,30,44,47,55,68,104,108,113,122],"context":[12],"vector-valued":[14,76],"repeated":[15],"games.":[16],"famous":[18],"Blackwells":[19],"theorem":[21],"prescribes":[22],"a":[23,34,38,86,97,140],"strategy":[24,91,106],"for":[25,28,71,92,127,134],"approachability,":[26],"i.e.,":[27],"steering":[29],"average":[31],"vector-cost":[32],"given":[35,39],"player":[36],"towards":[37],"target":[40],"set,":[41],"irrespective":[42],"strategies":[45],"other":[48],"players.":[49],"In":[50],"this":[51],"paper,":[52],"motivated":[53],"multi-objective":[56],"optimization":[57],"and":[58,88,132,137],"decision":[59],"making":[60],"problems":[61],"dynamically":[63],"changing":[64],"environments,":[65],"we":[66,84,95,125],"address":[67],"problem":[70],"Stackelberg":[72],"stochastic":[73],"games":[74],"with":[75],"cost":[77],"functions.":[78],"We":[79,118],"give":[80,85,96,126],"two":[81],"results.":[82],"First,":[83],"simple":[87],"computationally":[89],"tractable":[90],"approachability.":[93],"Second,":[94],"reinforcement":[98],"learning":[99],"based":[100],"algorithm":[101],"to":[102,112],"learn":[103],"approachable":[105],"when":[107],"transition":[109],"kernel":[110],"corresponding":[111],"underlying":[114],"dynamics":[115],"is":[116],"unknown.":[117],"also":[119],"show":[120],"that":[121,124],"conditions":[123],"are":[129],"both":[130],"necessary":[131],"sufficient":[133],"convex":[135],"sets":[136],"thus":[138],"giving":[139],"complete":[141],"characterization.":[142]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}