{"id":"https://openalex.org/W4411336629","doi":"https://doi.org/10.1109/tg.2025.3579719","title":"Exp3.P-Based Autonomous Decision Algorithm Against Nonstationary Opponents With Partially Known Policies","display_name":"Exp3.P-Based Autonomous Decision Algorithm Against Nonstationary Opponents With Partially Known Policies","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411336629","doi":"https://doi.org/10.1109/tg.2025.3579719"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2025.3579719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3579719","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","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/A5073920053","display_name":"Jin Zhu","orcid":"https://orcid.org/0000-0002-6038-4339"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zhu","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6038-4339","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059801528","display_name":"Chunhui Du","orcid":"https://orcid.org/0000-0001-8063-7711"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhui Du","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiacheng Chen","orcid":"https://orcid.org/0009-0006-6405-7753"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Chen","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-6405-7753","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056075825","display_name":"Lei Huang","orcid":"https://orcid.org/0000-0002-0322-6078"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Huang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061952552","display_name":"Geir E. Dullerud","orcid":"https://orcid.org/0000-0003-0596-6050"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geir E. Dullerud","raw_affiliation_strings":["Department of Mechanical Science and Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-0596-6050","affiliations":[{"raw_affiliation_string":"Department of Mechanical Science and Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84188996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"17","issue":"4","first_page":"975","last_page":"988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.6509000062942505,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.6509000062942505,"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/algorithm","display_name":"Algorithm","score":0.5154624581336975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4374557137489319},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.35034042596817017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3430117666721344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2645108699798584}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5154624581336975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4374557137489319},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.35034042596817017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3430117666721344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2645108699798584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2025.3579719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2025.3579719","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W157259654","https://openalex.org/W778742492","https://openalex.org/W2008809493","https://openalex.org/W2026829590","https://openalex.org/W2064675550","https://openalex.org/W2077902449","https://openalex.org/W2168405694","https://openalex.org/W2494793979","https://openalex.org/W2551398049","https://openalex.org/W2602275733","https://openalex.org/W2941095974","https://openalex.org/W2951360122","https://openalex.org/W2965433979","https://openalex.org/W3100191104","https://openalex.org/W4211208325","https://openalex.org/W4221008101","https://openalex.org/W4234228486","https://openalex.org/W4300961732","https://openalex.org/W4328007662","https://openalex.org/W4383268608","https://openalex.org/W4385338914","https://openalex.org/W4385627070","https://openalex.org/W4390814006","https://openalex.org/W4392477589","https://openalex.org/W4398226217","https://openalex.org/W4407589989"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"This":[0],"paper":[1],"takes":[2],"into":[3],"account":[4],"multi-agent":[5],"games":[6,45],"during":[7],"which":[8,61],"the":[9,81,87,98,113,118,122,127,132,150,153],"opponents":[10,48],"can":[11,33],"change":[12],"policies":[13],"and":[14,38,75,100,130,146],"their":[15],"policy":[16,28,71,89,102],"sets":[17],"are":[18],"partially":[19,50],"known.":[20],"Our":[21],"goal":[22],"is":[23,58,110],"to":[24,79],"generate":[25,80],"an":[26],"effective":[27],"such":[29,44],"that":[30],"our":[31],"agent":[32],"obtain":[34],"a":[35,104,136],"higher":[36],"reward":[37,124],"meanwhile":[39],"guarantee":[40],"bounded":[41,137],"regret.":[42,138],"Considering":[43],"against":[46],"non-stationary":[47],"with":[49],"known":[51],"policies,":[52],"Exp3.P-based":[53],"Autonomous":[54],"Decision":[55],"(EAD)":[56],"algorithm":[57,134],"put":[59],"forward":[60],"contains":[62],"three":[63],"steps.":[64],"Firstly,":[65],"we":[66,85,96],"learn":[67],"embedding":[68],"of":[69,121,152],"opponent":[70,88],"via":[72,103],"Conditional":[73],"Encoder-Decoder":[74],"employ":[76],"conditional":[77],"RL":[78],"targeted":[82,101,128],"policy.":[83],"Secondly,":[84],"estimate":[86],"through":[90],"online":[91],"Bayesian":[92],"belief":[93],"updates.":[94],"Finally,":[95],"select":[97],"adversarial":[99],"multi-armed":[105],"bandit":[106],"algorithm.":[107,115,156],"Theoretical":[108],"analysis":[109],"performed":[111],"for":[112],"EAD":[114,133,155],"We":[116],"give":[117],"lower":[119],"bound":[120],"expected":[123],"when":[125],"using":[126],"policy,":[129],"prove":[131],"has":[135],"Experimental":[139],"results":[140],"on":[141],"Kuhn":[142],"poker,":[143],"Grid-world":[144],"Predator-Prey":[145],"Grid":[147],"world":[148],"show":[149],"effectiveness":[151],"proposed":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-19T00:32:22.182498","created_date":"2025-10-10T00:00:00"}