{"id":"https://openalex.org/W4386815412","doi":"https://doi.org/10.14428/esann/2023.es2023-92","title":"Policy-Based Reinforcement Learning in the Generalized Rock-Paper-Scissors Game","display_name":"Policy-Based Reinforcement Learning in the Generalized Rock-Paper-Scissors Game","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815412","doi":"https://doi.org/10.14428/esann/2023.es2023-92"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-92","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-92","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-92","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2023.es2023-92","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092891758","display_name":"Imre Gergely Mali","orcid":null},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Imre Gergely Mali","raw_affiliation_strings":["Babe\u015f-Bolyai University, Department of Computer Science, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Babe\u015f-Bolyai University, Department of Computer Science, Romania","institution_ids":["https://openalex.org/I3125347698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052905844","display_name":"Gabriela Czibula","orcid":"https://orcid.org/0000-0001-7852-681X"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Gabriela Czibula","raw_affiliation_strings":["Babe-Bolyai University , Department of Computer Science , Romania","Babe-Bolyai University, Department of Computer Science, Romania","Babe\u015f-Bolyai University, Department of Computer Science, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Babe-Bolyai University , Department of Computer Science , Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Babe-Bolyai University, Department of Computer Science, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Babe\u015f-Bolyai University, Department of Computer Science, Romania","institution_ids":["https://openalex.org/I3125347698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.236,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58594433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9973999857902527,"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"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9973999857902527,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9941999912261963,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.991100013256073,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.796435534954071},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7065207958221436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6374661922454834},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6255332231521606},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.5579659342765808},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.539384126663208},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5240262150764465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46584782004356384},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.46402791142463684},{"id":"https://openalex.org/keywords/evolutionarily-stable-strategy","display_name":"Evolutionarily stable strategy","score":0.45598652958869934},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.4372681975364685},{"id":"https://openalex.org/keywords/combinatorial-game-theory","display_name":"Combinatorial game theory","score":0.431632399559021},{"id":"https://openalex.org/keywords/evolutionary-game-theory","display_name":"Evolutionary game theory","score":0.4261277914047241},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.20519664883613586},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09034141898155212}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.796435534954071},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7065207958221436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6374661922454834},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6255332231521606},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.5579659342765808},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.539384126663208},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5240262150764465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46584782004356384},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.46402791142463684},{"id":"https://openalex.org/C2519700","wikidata":"https://www.wikidata.org/wiki/Q1069992","display_name":"Evolutionarily stable strategy","level":3,"score":0.45598652958869934},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4372681975364685},{"id":"https://openalex.org/C102234262","wikidata":"https://www.wikidata.org/wiki/Q1320931","display_name":"Combinatorial game theory","level":4,"score":0.431632399559021},{"id":"https://openalex.org/C20249471","wikidata":"https://www.wikidata.org/wiki/Q2298789","display_name":"Evolutionary game theory","level":3,"score":0.4261277914047241},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.20519664883613586},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09034141898155212},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","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:10.14428/esann/2023.es2023-92","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-92","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-92","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-92","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-92","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-92","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G531579287","display_name":null,"funder_award_id":"PN-III-P4-ID-PCE-2020-0800","funder_id":"https://openalex.org/F4320318622","funder_display_name":"Ministerul Cercet\u0103rii, Inov\u0103rii \u015fi Digitaliz\u0103rii"},{"id":"https://openalex.org/G8253997468","display_name":null,"funder_award_id":"PN-III-P4-ID-PCE-2020-0800","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"}],"funders":[{"id":"https://openalex.org/F4320318622","display_name":"Ministerul Cercet\u0103rii, Inov\u0103rii \u015fi Digitaliz\u0103rii","ror":null},{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"},{"id":"https://openalex.org/F4320336189","display_name":"Colegiul Consultativ pentru Cercetare-Dezvoltare \u015fi Inovare","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815412.pdf","grobid_xml":"https://content.openalex.org/works/W4386815412.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2057807884","https://openalex.org/W2123742287","https://openalex.org/W2134053434","https://openalex.org/W2736601468","https://openalex.org/W2911934724","https://openalex.org/W2991046523","https://openalex.org/W3022861755","https://openalex.org/W3044015199","https://openalex.org/W3090386093","https://openalex.org/W3092984252","https://openalex.org/W3100660295","https://openalex.org/W3104881072","https://openalex.org/W3106570437","https://openalex.org/W3200705819","https://openalex.org/W4285816218","https://openalex.org/W4295150809","https://openalex.org/W4323570560"],"related_works":["https://openalex.org/W2374666693","https://openalex.org/W26097285","https://openalex.org/W3139383627","https://openalex.org/W2039104542","https://openalex.org/W2949341338","https://openalex.org/W4302440449","https://openalex.org/W2241833513","https://openalex.org/W2990217081","https://openalex.org/W4255020864","https://openalex.org/W2007563432"],"abstract_inverted_index":{"The":[0],"Rock-Paper-Scissors":[1],"game":[2,7,53],"is":[3,27],"a":[4,12,21],"popular":[5],"zero-sum":[6],"of":[8,20,24,28,49,96],"cyclic":[9,83],"nature,":[10],"with":[11,62,68,85],"mixed-strategy":[13],"Nash-equilibrium":[14],"that":[15],"has":[16],"been":[17],"the":[18,46,52],"subject":[19],"large":[22],"number":[23],"studies":[25,40,67],"and":[26,34,44,58,74],"particular":[29],"interest":[30],"for":[31],"economy,":[32],"sociology":[33],"artificial":[35],"intelligence.While":[36],"there":[37],"are":[38,72],"numerous":[39],"exploring":[41],"evolutionary":[42],"dynamics":[43],"learning,":[45],"overwhelming":[47],"majority":[48],"these":[50,97],"consider":[51],"in":[54],"its":[55],"classical":[56],"form,":[57],"two":[59,88],"important":[60],"axes":[61],"potential":[63],"relevance":[64],"remain":[65],"unexplored.First,":[66],"policy-based":[69],"reinforcement":[70],"algorithms":[71],"lacking,":[73],"second,":[75],"few":[76],"existing":[77],"investigations":[78],"attempted":[79],"to":[80,93],"study":[81],"such":[82],"games":[84],"more":[86],"than":[87],"players.The":[89],"present":[90],"work":[91],"aims":[92],"address":[94],"both":[95],"matters.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}