{"id":"https://openalex.org/W2995864482","doi":"https://doi.org/10.1080/10556788.2019.1695131","title":"Towards solving 2-TBSG efficiently","display_name":"Towards solving 2-TBSG efficiently","publication_year":2019,"publication_date":"2019-12-10","ids":{"openalex":"https://openalex.org/W2995864482","doi":"https://doi.org/10.1080/10556788.2019.1695131","mag":"2995864482"},"language":"en","primary_location":{"id":"doi:10.1080/10556788.2019.1695131","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10556788.2019.1695131","pdf_url":null,"source":{"id":"https://openalex.org/S103047102","display_name":"Optimization methods & software","issn_l":"1026-7670","issn":["1026-7670","1029-4937","1055-6788"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Optimization Methods and Software","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/A5018020501","display_name":"Zeyu Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Jia","raw_affiliation_strings":["School of Mathematical Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006127137","display_name":"Zaiwen Wen","orcid":"https://orcid.org/0000-0003-1762-0671"},"institutions":[{"id":"https://openalex.org/I4210133846","display_name":"Peking University International Hospital","ror":"https://ror.org/03jxhcr96","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210133846"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zaiwen Wen","raw_affiliation_strings":["Beijing International Center for Mathematical Research, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing International Center for Mathematical Research, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210133846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041526408","display_name":"Yinyu Ye","orcid":"https://orcid.org/0009-0001-3239-2622"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinyu Ye","raw_affiliation_strings":["Department of Management Science and Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Management Science and Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006127137"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210133846"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5918302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"35","issue":"4","first_page":"706","last_page":"721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11031","display_name":"Game Theory and Applications","score":0.9958999752998352,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9814000129699707,"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/simplex","display_name":"Simplex","score":0.6934378743171692},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6569656729698181},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6505559086799622},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.54262375831604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5314784049987793},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5131531357765198},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.4886208176612854},{"id":"https://openalex.org/keywords/simplex-algorithm","display_name":"Simplex algorithm","score":0.4550940692424774},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.43764159083366394},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4310106337070465},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.4300711452960968},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37002596259117126},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2648659348487854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2345390021800995},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.22404181957244873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18122345209121704},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13127025961875916}],"concepts":[{"id":"https://openalex.org/C62438384","wikidata":"https://www.wikidata.org/wiki/Q331350","display_name":"Simplex","level":2,"score":0.6934378743171692},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6569656729698181},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6505559086799622},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.54262375831604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5314784049987793},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5131531357765198},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.4886208176612854},{"id":"https://openalex.org/C144521790","wikidata":"https://www.wikidata.org/wiki/Q134164","display_name":"Simplex algorithm","level":3,"score":0.4550940692424774},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.43764159083366394},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4310106337070465},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4300711452960968},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37002596259117126},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2648659348487854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2345390021800995},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.22404181957244873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18122345209121704},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13127025961875916},{"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/10556788.2019.1695131","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10556788.2019.1695131","pdf_url":null,"source":{"id":"https://openalex.org/S103047102","display_name":"Optimization methods & software","issn_l":"1026-7670","issn":["1026-7670","1029-4937","1055-6788"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Optimization Methods and Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.46000000834465027,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G2030148605","display_name":null,"funder_award_id":"11831002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1480317510","https://openalex.org/W1496590343","https://openalex.org/W1928484725","https://openalex.org/W1984901446","https://openalex.org/W2034413058","https://openalex.org/W2098432798","https://openalex.org/W2100114422","https://openalex.org/W2107924392","https://openalex.org/W2119567691","https://openalex.org/W2141076336","https://openalex.org/W2141252092","https://openalex.org/W2167471538","https://openalex.org/W2257979135","https://openalex.org/W2569529055","https://openalex.org/W4237591687","https://openalex.org/W4254547512"],"related_works":["https://openalex.org/W2185826091","https://openalex.org/W2048470382","https://openalex.org/W2477407501","https://openalex.org/W2384679317","https://openalex.org/W2911215968","https://openalex.org/W1570109187","https://openalex.org/W1583787753","https://openalex.org/W2491692165","https://openalex.org/W2366013513","https://openalex.org/W4244786412"],"abstract_inverted_index":{"Two-player":[0],"turn-based":[1],"stochastic":[2],"game":[3,8],"(2-TBSG)":[4],"is":[5,17,41,59],"a":[6,60,67,78,92,102,119,133],"two-player":[7],"model":[9],"which":[10],"aims":[11],"to":[12,52,101,135],"find":[13],"Nash":[14],"equilibriums":[15],"and":[16,23,91,126],"widely":[18],"utilized":[19],"in":[20,89],"reinforcement":[21],"learning":[22],"AI.":[24],"Inspired":[25],"by":[26,117],"the":[27,30,35,46,82,110,123,127],"fact":[28],"that":[29],"simplex":[31,68,79,94],"method":[32,134],"for":[33,63],"solving":[34],"deterministic":[36],"discounted":[37],"Markov":[38],"decision":[39],"processes":[40],"strongly":[42,111],"polynomial":[43,112],"independent":[44],"of":[45,98,104,114],"discount":[47],"factor,":[48],"we":[49,131],"are":[50],"trying":[51],"answer":[53],"an":[54,86],"open":[55],"problem":[56],"whether":[57],"there":[58],"similar":[61],"algorithm":[62],"2-TBSG.":[64],"We":[65,108],"develop":[66],"strategy":[69,76,95,120,125],"iteration":[70],"where":[71,142],"one":[72],"player":[73,84],"updates":[74],"its":[75],"with":[77],"step":[80],"while":[81],"other":[83],"finds":[85],"optimal":[87],"counterstrategy":[88],"turn,":[90],"modified":[93],"iteration.":[96],"Both":[97],"them":[99],"belong":[100],"class":[103],"geometrically":[105],"converging":[106],"algorithms.":[107],"establish":[109],"property":[113],"these":[115],"algorithms":[116],"considering":[118],"combined":[121],"from":[122],"current":[124],"equilibrium":[128],"strategy.":[129],"Moreover,":[130],"present":[132],"transform":[136],"general":[137],"2-TBSGs":[138,141],"into":[139],"special":[140],"each":[143],"state":[144],"has":[145],"exactly":[146],"two":[147],"actions.":[148]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}