{"id":"https://openalex.org/W4372260032","doi":"https://doi.org/10.1109/icassp49357.2023.10096125","title":"Progressive Diversifying Policy for Multi-Agent Reinforcement Learning","display_name":"Progressive Diversifying Policy for Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260032","doi":"https://doi.org/10.1109/icassp49357.2023.10096125"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5114778037","display_name":"Shaoqi Sun","orcid":"https://orcid.org/0009-0005-9656-6918"},"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"]},{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoqi Sun","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China","Key Laboratory of Software Engineering for Complex Systems, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China","institution_ids":["https://openalex.org/I198357462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073132517","display_name":"Yuanzhao Zhai","orcid":"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"]},{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhao Zhai","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China","Key Laboratory of Software Engineering for Complex Systems, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China","institution_ids":["https://openalex.org/I198357462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"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"]},{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China","Key Laboratory of Software Engineering for Complex Systems, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China","institution_ids":["https://openalex.org/I198357462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"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"]},{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","Key Laboratory of Software Engineering for Complex Systems, Changsha, China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China","institution_ids":["https://openalex.org/I198357462"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"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"]},{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","Key Laboratory of Software Engineering for Complex Systems, Changsha, China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Key Laboratory of Software Engineering for Complex Systems, Changsha, China","institution_ids":["https://openalex.org/I198357462"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965999722480774,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9779000282287598,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8289929032325745},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6185336112976074},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5715963840484619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3108441233634949},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13460996747016907},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05379334092140198}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8289929032325745},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6185336112976074},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5715963840484619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3108441233634949},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13460996747016907},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05379334092140198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2033178790","https://openalex.org/W2086234878","https://openalex.org/W2105767494","https://openalex.org/W2107726111","https://openalex.org/W2120636621","https://openalex.org/W2396783599","https://openalex.org/W2509924317","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2768629321","https://openalex.org/W2892258706","https://openalex.org/W2945442007","https://openalex.org/W2964067469","https://openalex.org/W3103635569","https://openalex.org/W3106539628","https://openalex.org/W3170473100","https://openalex.org/W3193434518","https://openalex.org/W4286748781","https://openalex.org/W4288594419","https://openalex.org/W6627932998","https://openalex.org/W6678007500","https://openalex.org/W6712348848","https://openalex.org/W6741002519","https://openalex.org/W6756303580","https://openalex.org/W6758846586","https://openalex.org/W6771876938","https://openalex.org/W6804514601","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Multi-Agent":[0],"Reinforcement":[1],"Learning":[2],"(MARL)":[3],"has":[4],"recently":[5],"achieved":[6],"promising":[7],"performance":[8,126],"in":[9,52],"many":[10],"collaborative":[11],"decision":[12],"making":[13],"tasks.":[14],"However,":[15],"one":[16],"of":[17,27,37,108],"the":[18,25,28,35,61,93,105,118],"main":[19],"bottleneck":[20],"challenges":[21],"for":[22,76],"MARL":[23,115],"is":[24],"sparsity":[26],"team":[29,90,101],"reward,":[30],"which":[31],"can":[32,98,123],"lead":[33],"to":[34,58,86],"homogenization":[36],"agents\u2019":[38,64],"behaviors.":[39],"To":[40],"address":[41],"these":[42],"issues,":[43],"we":[44,56,79],"propose":[45,57,80],"a":[46,81,88,129],"Progressive":[47],"Diversifying":[48],"Policy":[49],"(PDP)":[50],"algorithm":[51],"this":[53],"paper.":[54],"Specifically,":[55],"actively":[59],"amplify":[60],"diversity":[62,70,83],"between":[63],"policies":[65],"during":[66],"learning":[67],"and":[68,103,117],"exploit":[69],"as":[71],"an":[72],"additional":[73],"intrinsic":[74],"reward":[75],"MARL.":[77],"Furthermore,":[78],"progressive":[82],"boosting":[84],"policy":[85],"find":[87],"better":[89],"policy.":[91],"Leveraging":[92],"aforementioned":[94],"improvements,":[95],"our":[96],"method":[97],"handle":[99],"sparse":[100],"rewards":[102],"alleviate":[104],"homogeneous":[106],"behaviors":[107],"agents.":[109],"We":[110],"conduct":[111],"experiments":[112],"on":[113],"widely-used":[114],"environments":[116],"results":[119],"show":[120],"that":[121],"PDP":[122],"provide":[124],"state-of-the-art":[125],"while":[127],"maintaining":[128],"competitive":[130],"convergence":[131],"speed.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
