{"id":"https://openalex.org/W4205886511","doi":"https://doi.org/10.1109/smc52423.2021.9659219","title":"Distributed Reinforcement Learning with Self-Play in Parameterized Action Space","display_name":"Distributed Reinforcement Learning with Self-Play in Parameterized Action Space","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4205886511","doi":"https://doi.org/10.1109/smc52423.2021.9659219"},"language":"en","primary_location":{"id":"doi:10.1109/smc52423.2021.9659219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9659219","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101997874","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0003-2258-0854"},"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":"Jun Ma","raw_affiliation_strings":["School of Data Science, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055919855","display_name":"Shunyi Yao","orcid":null},"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":"Shunyi Yao","raw_affiliation_strings":["School of Computer Science and Technology, USTC, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006045871","display_name":"Guangda Chen","orcid":"https://orcid.org/0000-0003-1888-9947"},"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":"Guangda Chen","raw_affiliation_strings":["School of Computer Science and Technology, USTC, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003495696","display_name":"Jiakai Song","orcid":null},"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":"Jiakai Song","raw_affiliation_strings":["School of Computer Science and Technology, USTC, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061104105","display_name":"Jianmin Ji","orcid":"https://orcid.org/0000-0002-1515-0402"},"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":"Jianmin Ji","raw_affiliation_strings":["School of Computer Science and Technology, USTC, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64582959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"1178","last_page":"1185"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9639999866485596,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9552000164985657,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9292770028114319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7960038185119629},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6167494058609009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.615276575088501},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5969109535217285},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5503506064414978},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5490926504135132},{"id":"https://openalex.org/keywords/league","display_name":"League","score":0.46667659282684326},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4624834656715393},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4538421034812927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43007510900497437},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32012414932250977},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08261984586715698}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9292770028114319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960038185119629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6167494058609009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.615276575088501},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5969109535217285},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5503506064414978},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5490926504135132},{"id":"https://openalex.org/C207456731","wikidata":"https://www.wikidata.org/wiki/Q660818","display_name":"League","level":2,"score":0.46667659282684326},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4624834656715393},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4538421034812927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43007510900497437},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32012414932250977},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08261984586715698},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc52423.2021.9659219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9659219","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326665","display_name":"Anhui Provincial Development and Reform Commission","ror":"https://ror.org/01jxa2z23"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W2145339207","https://openalex.org/W2154207916","https://openalex.org/W2167932310","https://openalex.org/W2168281471","https://openalex.org/W2256420211","https://openalex.org/W2257979135","https://openalex.org/W2603088459","https://openalex.org/W2736601468","https://openalex.org/W2739657930","https://openalex.org/W2766447205","https://openalex.org/W2786928559","https://openalex.org/W2798705390","https://openalex.org/W2897417898","https://openalex.org/W2944306386","https://openalex.org/W2963616477","https://openalex.org/W2964164283","https://openalex.org/W2964896545","https://openalex.org/W2965676832","https://openalex.org/W2965757358","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3110282614","https://openalex.org/W3110446646","https://openalex.org/W3112673853","https://openalex.org/W3114657141","https://openalex.org/W3147968035","https://openalex.org/W3177368174","https://openalex.org/W3181074849","https://openalex.org/W6607231233","https://openalex.org/W6636881020","https://openalex.org/W6684614773","https://openalex.org/W6684636268","https://openalex.org/W6691861496","https://openalex.org/W6692312642","https://openalex.org/W6696772115","https://openalex.org/W6735789912","https://openalex.org/W6741002519","https://openalex.org/W6748554570","https://openalex.org/W6755326576","https://openalex.org/W6762592680","https://openalex.org/W6772005887","https://openalex.org/W6786098777","https://openalex.org/W6786918259","https://openalex.org/W6797776478"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W4389016272","https://openalex.org/W2285591800","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4321354283","https://openalex.org/W4255576661"],"abstract_inverted_index":{"Self-play":[0],"has":[1],"been":[2],"shown":[3],"to":[4,7,50,89,128],"be":[5],"effective":[6,118],"provide":[8],"a":[9,14,74,98,103],"proper":[10],"training":[11,77],"curriculum":[12],"for":[13,31,42,58,79],"reinforcement":[15,55,130],"learning":[16,131],"agent":[17],"in":[18,44,54,91],"competitive":[19],"multi-agent":[20],"environments":[21],"without":[22],"direct":[23],"supervision.":[24],"However,":[25],"its":[26],"performance":[27],"is":[28,48,117,136],"still":[29],"unstable":[30],"problems":[32],"with":[33,40,65],"sparse":[34],"rewards,":[35],"e.g.,":[36],"the":[37,107,115],"scoring":[38],"task":[39],"goalkeeper":[41],"robots":[43],"RoboCup":[45,111],"soccer.":[46],"It":[47],"challenging":[49],"solve":[51],"these":[52,70],"tasks":[53],"learning,":[56],"especially":[57],"those":[59],"that":[60,87],"require":[61],"combining":[62],"high-level":[63],"actions":[64],"flexible":[66],"control.":[67],"To":[68],"address":[69],"challenges,":[71],"we":[72],"introduce":[73],"distributed":[75],"self-play":[76],"framework":[78],"an":[80],"extended":[81],"proximal":[82],"policy":[83],"optimization":[84],"(PPO)":[85],"algorithm":[86],"learns":[88,120],"act":[90],"parameterized":[92],"action":[93],"space":[94],"and":[95,119],"plays":[96],"against":[97,124],"group":[99],"of":[100,109],"opponents,":[101],"i.e.,":[102],"league.":[104],"Experiments":[105],"on":[106],"domain":[108],"simulated":[110],"soccer":[112],"show":[113],"that,":[114],"approach":[116],"more":[121],"robust":[122],"policies":[123],"various":[125],"opponents":[126],"compared":[127],"existing":[129],"methods.":[132],"A":[133],"demonstration":[134],"video":[135],"available":[137],"online":[138],"at":[139],"https://youtu.be/BuLli1vND4.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}