{"id":"https://openalex.org/W3145840617","doi":"https://doi.org/10.1016/j.neucom.2021.04.006","title":"Self-play reinforcement learning with comprehensive critic in computer games","display_name":"Self-play reinforcement learning with comprehensive critic in computer games","publication_year":2021,"publication_date":"2021-04-06","ids":{"openalex":"https://openalex.org/W3145840617","doi":"https://doi.org/10.1016/j.neucom.2021.04.006","mag":"3145840617"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2021.04.006","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2021.04.006","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","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/A5031053184","display_name":"Shanqi Liu","orcid":"https://orcid.org/0000-0003-0583-2423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanqi Liu","raw_affiliation_strings":["Institute of Cyber Systems and Control, ZheJiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, ZheJiang University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056945088","display_name":"Junjie Cao","orcid":"https://orcid.org/0000-0003-0484-8167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Cao","raw_affiliation_strings":["Institute of Cyber Systems and Control, ZheJiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, ZheJiang University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114500332","display_name":"Yujie Wang","orcid":"https://orcid.org/0009-0003-0310-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujie Wang","raw_affiliation_strings":["Institute of Cyber Systems and Control, ZheJiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, ZheJiang University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004120702","display_name":"Wenzhou Chen","orcid":"https://orcid.org/0000-0002-1443-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhou Chen","raw_affiliation_strings":["Institute of Cyber Systems and Control, ZheJiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, ZheJiang University, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Institute of Cyber Systems and Control, ZheJiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, ZheJiang University, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100724297"],"corresponding_institution_ids":[],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":3.5,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93659727,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"449","issue":null,"first_page":"207","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9829999804496765,"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":0.9166780710220337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8122062683105469},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5830461978912354},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5827602744102478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5457214713096619},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5455302000045776},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5091943144798279},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.4686562120914459},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3987564444541931},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0873120129108429},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08483478426933289}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9166780710220337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122062683105469},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5830461978912354},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5827602744102478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457214713096619},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5455302000045776},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5091943144798279},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.4686562120914459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3987564444541931},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0873120129108429},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08483478426933289},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","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:10.1016/j.neucom.2021.04.006","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2021.04.006","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1499747339","https://openalex.org/W1542941925","https://openalex.org/W1999035253","https://openalex.org/W2103196307","https://openalex.org/W2116234938","https://openalex.org/W2119717200","https://openalex.org/W2138178898","https://openalex.org/W2144274908","https://openalex.org/W2153678894","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2208149249","https://openalex.org/W2257979135","https://openalex.org/W2522489477","https://openalex.org/W2588645044","https://openalex.org/W2766447205","https://openalex.org/W2785556016","https://openalex.org/W2887897884","https://openalex.org/W2960876848","https://openalex.org/W2962747693","https://openalex.org/W2963407617","https://openalex.org/W2964223369","https://openalex.org/W2975052530","https://openalex.org/W2982333832","https://openalex.org/W3037207827","https://openalex.org/W3047972188","https://openalex.org/W3100860002","https://openalex.org/W3107951310","https://openalex.org/W3118210634","https://openalex.org/W6601765238","https://openalex.org/W6601867051","https://openalex.org/W6603932791","https://openalex.org/W6609795279","https://openalex.org/W6677436153","https://openalex.org/W6727252785","https://openalex.org/W6753814663","https://openalex.org/W6814003322","https://openalex.org/W6835070974","https://openalex.org/W6868356770"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2145796981","https://openalex.org/W2900431508","https://openalex.org/W2050340470"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}
