{"id":"https://openalex.org/W3009015155","doi":"https://doi.org/10.1109/ssci44817.2019.9002811","title":"Deep Reinforcement Learning Based Intelligent Decision Making for Two-player Sequential Game with Uncertain Irrational Player","display_name":"Deep Reinforcement Learning Based Intelligent Decision Making for Two-player Sequential Game with Uncertain Irrational Player","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3009015155","doi":"https://doi.org/10.1109/ssci44817.2019.9002811","mag":"3009015155"},"language":"en","primary_location":{"id":"doi:10.1109/ssci44817.2019.9002811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5088809666","display_name":"Zejian Zhou","orcid":"https://orcid.org/0000-0002-0252-6765"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zejian Zhou","raw_affiliation_strings":["Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100717012","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0003-4130-7925"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":["Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Biomedical Engineering, University of Nevada, Reno, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134113660"],"apc_list":null,"apc_paid":null,"fwci":0.2893,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69049934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"9","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9592000246047974,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.946399986743927,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7935321927070618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7221276164054871},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.6929718255996704},{"id":"https://openalex.org/keywords/irrationality","display_name":"Irrationality","score":0.6446363925933838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6157789826393127},{"id":"https://openalex.org/keywords/irrational-number","display_name":"Irrational number","score":0.4902241826057434},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4779622256755829},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36743277311325073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3393363356590271},{"id":"https://openalex.org/keywords/rationality","display_name":"Rationality","score":0.174098938703537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13139724731445312},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.08231142163276672}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7935321927070618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7221276164054871},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.6929718255996704},{"id":"https://openalex.org/C2777019708","wikidata":"https://www.wikidata.org/wiki/Q1412340","display_name":"Irrationality","level":3,"score":0.6446363925933838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6157789826393127},{"id":"https://openalex.org/C94931360","wikidata":"https://www.wikidata.org/wiki/Q607728","display_name":"Irrational number","level":2,"score":0.4902241826057434},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4779622256755829},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36743277311325073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393363356590271},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.174098938703537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13139724731445312},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.08231142163276672},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci44817.2019.9002811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1641379095","https://openalex.org/W1757796397","https://openalex.org/W2104602264","https://openalex.org/W2144274908","https://openalex.org/W2165150801","https://openalex.org/W2291986326","https://openalex.org/W2518713116","https://openalex.org/W2913130183","https://openalex.org/W2963407617","https://openalex.org/W2963625099","https://openalex.org/W2963937357","https://openalex.org/W2964164283","https://openalex.org/W4234008654","https://openalex.org/W4293862243","https://openalex.org/W4297789683","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W6630520071","https://openalex.org/W6631168379","https://openalex.org/W6637967152","https://openalex.org/W6675811377","https://openalex.org/W6681187623","https://openalex.org/W6684205842","https://openalex.org/W6696772115","https://openalex.org/W6726754200","https://openalex.org/W6738796088","https://openalex.org/W6743367460"],"related_works":["https://openalex.org/W46383765","https://openalex.org/W2195589646","https://openalex.org/W2401297194","https://openalex.org/W2381515689","https://openalex.org/W4250299898","https://openalex.org/W2079936830","https://openalex.org/W2026699385","https://openalex.org/W3120892761","https://openalex.org/W2392439378","https://openalex.org/W2362263755"],"abstract_inverted_index":{"In":[0,22],"this":[1,63],"paper,":[2],"two":[3,72],"player":[4,12],"sequential":[5],"game":[6],"with":[7,41,108],"an":[8],"unknown":[9],"non-stationary":[10],"irrational":[11],"is":[13,81,101,133],"investigated":[14],"for":[15,37],"cooperative":[16,39,142],"autonomous":[17],"robots":[18],"decision":[19,34],"making":[20,35],"applications.":[21],"practice,":[23],"the":[24,31,53,86,95,105,117,140,148,170,173],"irrationality":[25,48],"of":[26,33,89,119,172],"agent":[27],"can":[28,49,138],"seriously":[29],"degrade":[30],"effectiveness":[32,171],"especially":[36],"distributed":[38],"tasks":[40],"applications":[42],"to":[43,83,103,110,168],"multi-robot":[44],"systems.":[45],"Specifically,":[46],"The":[47,135],"be":[50],"caused":[51],"by":[52,151],"cooperation":[54,76,90,113],"agent's":[55],"mechanical":[56],"failure":[57],"or":[58,91,121],"sensor":[59],"flaw.":[60],"To":[61],"handle":[62],"issue,":[64],"a":[65,111,124,154],"novel":[66,125],"dynamic":[67],"evaluation":[68],"system,":[69],"which":[70],"includes":[71],"important":[73],"parameters,":[74],"i.e.":[75],"index":[77],"and":[78,163],"competitive":[79],"flag,":[80],"designed":[82,136,174],"efficiently":[84],"quantify":[85],"player's":[87],"level":[88,143],"competition":[92],"firstly.":[93],"Then,":[94],"continuous":[96,112,155],"deep":[97,129,156],"Q":[98,157],"network":[99,158],"space":[100],"proposed":[102],"predict":[104],"action":[106],"value":[107],"respect":[109],"index.":[114],"Inspired":[115],"from":[116],"framework":[118],"\"Friend":[120],"Foe\"":[122],"algorithm,":[123],"hybrid":[126],"online":[127],"multi-agent":[128],"reinforcement":[130],"learning":[131,152],"algorithm":[132,137],"proposed.":[134],"evaluate":[139],"cooperator's":[141],"as":[144,146],"well":[145],"maximize":[147],"total":[149],"payoff":[150],"in":[153],"space.":[159],"Eventually,":[160],"numerical":[161],"simulation":[162],"experimental":[164],"tests":[165],"are":[166],"provided":[167],"demonstrate":[169],"algorithm.":[175]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}