{"id":"https://openalex.org/W4366308309","doi":"https://doi.org/10.1109/ictai56018.2022.00182","title":"Exploring Policy Diversity in Parallel Actor-Critic Learning","display_name":"Exploring Policy Diversity in Parallel Actor-Critic Learning","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4366308309","doi":"https://doi.org/10.1109/ictai56018.2022.00182"},"language":"en","primary_location":{"id":"doi:10.1109/ictai56018.2022.00182","doi":"https://doi.org/10.1109/ictai56018.2022.00182","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai56018.2022.00182","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5076057630","display_name":"Yanqiang Zhang","orcid":"https://orcid.org/0000-0001-5577-0529","observed_orcids":["https://orcid.org/0000-0001-5577-0529"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqiang Zhang","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073132517","display_name":"Yuanzhao Zhai","orcid":"https://orcid.org/0000-0003-1385-0074","observed_orcids":["https://orcid.org/0000-0003-1385-0074"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhao Zhai","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014613047","display_name":"Gongqian Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongqian Zhou","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318","observed_orcids":["https://orcid.org/0000-0002-1236-8318"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905","observed_orcids":["https://orcid.org/0000-0002-7587-8905","https://orcid.org/0000-0002-1687-0970"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Songwang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songwang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1048,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.25010772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"30","issue":null,"first_page":"1196","last_page":"1203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/policy-diversity","display_name":"policy diversity","score":0.8199999928474426},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.5820000171661377},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.7839999794960022},{"id":"https://openalex.org/keywords/kullback-leibler-divergence","display_name":"Kullback-Leibler divergence","score":0.8669999837875366},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.8709999918937683},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.6679999828338623},{"id":"https://openalex.org/keywords/procedural-content-generation","display_name":"procedural content generation","score":0.3540000021457672},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8730000257492065}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8210662603378296},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.7842093706130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589004635810852},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5816217660903931},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5552644729614258},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5400636196136475},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49782323837280273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442351162433624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36224713921546936},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32798606157302856},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.08678829669952393},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.08438146114349365},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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:10.1109/ictai56018.2022.00182","doi":"https://doi.org/10.1109/ictai56018.2022.00182","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai56018.2022.00182","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1583833196","https://openalex.org/W1988526405","https://openalex.org/W2260756217","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2559655401","https://openalex.org/W2593658277","https://openalex.org/W2593766708","https://openalex.org/W2614839826","https://openalex.org/W2776124380","https://openalex.org/W2786036274","https://openalex.org/W2788741142","https://openalex.org/W2809668646","https://openalex.org/W2891790128","https://openalex.org/W2898436992","https://openalex.org/W2899205164","https://openalex.org/W2903181768","https://openalex.org/W2913854057","https://openalex.org/W2914898814","https://openalex.org/W2948199691","https://openalex.org/W2963276097","https://openalex.org/W2963761387","https://openalex.org/W2964067469","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2994073215","https://openalex.org/W2996110979","https://openalex.org/W3128522352","https://openalex.org/W3131511400","https://openalex.org/W3132970947","https://openalex.org/W3170059879","https://openalex.org/W6744419923","https://openalex.org/W6779129966","https://openalex.org/W6780225908","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W3032956793","https://openalex.org/W3128522352","https://openalex.org/W4417230782","https://openalex.org/W7010474987","https://openalex.org/W4412717546","https://openalex.org/W4391020172","https://openalex.org/W2999262846","https://openalex.org/W4393159854","https://openalex.org/W3172611114","https://openalex.org/W7061908026"],"abstract_inverted_index":{"Exploration":[0],"is":[1,50],"a":[2,80,102],"critical":[3],"challenge":[4],"for":[5,85],"deep":[6],"reinforcement":[7],"learning":[8],"methods.":[9],"Although":[10],"existing":[11],"works":[12],"such":[13],"as":[14,122],"actor-critic":[15,94],"algorithms":[16],"have":[17],"made":[18],"much":[19],"progress,":[20],"most":[21],"still":[22],"suffer":[23],"from":[24],"the":[25,43,48,68,71,92,97,112,115,123,156],"sample":[26,56,164],"inefficiency":[27],"problem":[28],"in":[29,137,155,158],"complex":[30],"environments":[31],"where":[32],"rewards":[33,162],"are":[34],"sparse.":[35],"Parallel":[36],"sampling,":[37],"which":[38,65],"uses":[39],"multiple":[40,138],"actors":[41,61,121,128],"with":[42,47,145],"same":[44],"policy":[45],"interacting":[46],"environment,":[49],"an":[51],"effective":[52],"approach":[53,84,136],"to":[54,96,126,129],"improve":[55],"efficiency.":[57,165],"However,":[58],"parallel":[59,86,93,106,120],"parameter-sharing":[60],"collect":[62],"similar":[63],"samples,":[64],"generally":[66],"hinders":[67],"improvement":[69],"of":[70,101,114,160],"overall":[72],"exploration":[73],"process.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,90,110],"propose":[79],"Policy":[81],"Diversity":[82],"enhanced":[83],"Actor-Critic":[87],"(PDAC).":[88],"Specifically,":[89],"extend":[91],"architecture":[95],"PDAC":[98,151],"framework":[99],"composed":[100],"shared":[103],"critic":[104],"and":[105,142,163],"distinct":[107],"actors.":[108],"Then":[109],"introduce":[111],"KL-divergence":[113],"action":[116],"probability":[117],"distribution":[118],"between":[119],"intrinsic":[124],"reward":[125],"encourage":[127],"explore":[130],"diverse":[131],"strategies.":[132],"We":[133],"evaluate":[134],"our":[135],"challenging":[139],"procedurally-generated":[140],"tasks":[141],"compare":[143],"it":[144],"state-of-the-art":[146],"algorithms.":[147],"Experiments":[148],"show":[149],"that":[150],"makes":[152],"significant":[153],"progress":[154],"comparison,":[157],"terms":[159],"cumulative":[161]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-04-20T00:00:00"}