{"id":"https://openalex.org/W2999262846","doi":"https://doi.org/10.1109/iwcia47330.2019.8955073","title":"Diversifying experiences in multi agent reinforcement learning","display_name":"Diversifying experiences in multi agent reinforcement learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2999262846","doi":"https://doi.org/10.1109/iwcia47330.2019.8955073","mag":"2999262846"},"language":"en","primary_location":{"id":"doi:10.1109/iwcia47330.2019.8955073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia47330.2019.8955073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","raw_type":"proceedings-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/A5040698241","display_name":"Nagar Anthel Venkatesh Suryanarayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"N.A.V Suryanarayanan","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005925953","display_name":"Hitoshi Iba","orcid":"https://orcid.org/0000-0001-7815-0306"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Iba Hitoshi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo, Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17968529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"47","last_page":"52"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9947999715805054,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.98580002784729,"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":0.9186257123947144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7659250497817993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5981574654579163},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48124265670776367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.456132709980011},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.4384703040122986},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4242256283760071}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9186257123947144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659250497817993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5981574654579163},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48124265670776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.456132709980011},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.4384703040122986},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4242256283760071},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcia47330.2019.8955073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia47330.2019.8955073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1518858799","https://openalex.org/W1542941925","https://openalex.org/W2046376809","https://openalex.org/W2090933635","https://openalex.org/W2107544712","https://openalex.org/W2111935653","https://openalex.org/W2114537044","https://openalex.org/W2119717200","https://openalex.org/W2290354866","https://openalex.org/W2505954521","https://openalex.org/W2596367596","https://openalex.org/W2772721022","https://openalex.org/W2779977383","https://openalex.org/W2781726626","https://openalex.org/W2782916326","https://openalex.org/W2894662639","https://openalex.org/W2950471160","https://openalex.org/W2951799422","https://openalex.org/W2963790038","https://openalex.org/W2963864421","https://openalex.org/W2963937357","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W4241901489","https://openalex.org/W4297789683","https://openalex.org/W4299802797","https://openalex.org/W4300799055","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6743367460"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"learning":[2],"algorithms":[3,21,45],"have":[4,22,80],"traditionally":[5],"been":[6,23],"applied":[7],"to":[8,25,36,47,100],"tasks":[9],"that":[10,96],"train":[11,26],"challenging":[12],"control":[13],"behavior.":[14],"Actor":[15],"Critic":[16],"based":[17,91],"versions":[18],"of":[19,30],"these":[20,44],"used":[24],"agents":[27],"in":[28,40,50],"state":[29],"the":[31,51,57,61,65,72,107],"art":[32],"settings.":[33],"While":[34],"proving":[35],"be":[37],"sample":[38],"efficient":[39],"multi":[41],"agent":[42],"learning,":[43],"tend":[46],"perform":[48],"poorly":[49],"exploration":[52,66],"phases.":[53],"In":[54],"this":[55,82],"paper,":[56],"experience":[58],"gained":[59],"by":[60,70],"replay":[62],"buffer":[63],"during":[64],"phase":[67],"is":[68],"improved":[69],"diversifying":[71],"input":[73],"results":[74],"using":[75],"a":[76,102],"genetic":[77],"algorithm.":[78],"We":[79],"tested":[81],"method":[83,98],"on":[84],"predator":[85],"prey":[86],"environment":[87],"and":[88],"other":[89],"team":[90],"tasks.":[92],"The":[93],"evaluation":[94],"shows":[95],"our":[97],"tends":[99],"produce":[101],"more":[103],"robust":[104],"solutions":[105],"outperforming":[106],"traditional":[108],"methods.":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}