{"id":"https://openalex.org/W4406460533","doi":"https://doi.org/10.1109/bigdata62323.2024.10826072","title":"Modular Deep Reinforcement Learning: Enhancing Flexibility through Agent Splitting","display_name":"Modular Deep Reinforcement Learning: Enhancing Flexibility through Agent Splitting","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406460533","doi":"https://doi.org/10.1109/bigdata62323.2024.10826072"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10826072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5100589865","display_name":"Chong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I137853757","display_name":"Howard University","ror":"https://ror.org/05gt1vc06","country_code":"US","type":"education","lineage":["https://openalex.org/I137853757"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chong Tian","raw_affiliation_strings":["Howard University,Dept. of Electrical Engineering & Computer Science,Washington, DC,USA"],"affiliations":[{"raw_affiliation_string":"Howard University,Dept. of Electrical Engineering & Computer Science,Washington, DC,USA","institution_ids":["https://openalex.org/I137853757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046343080","display_name":"Danda B. Rawat","orcid":"https://orcid.org/0000-0003-3638-3464"},"institutions":[{"id":"https://openalex.org/I137853757","display_name":"Howard University","ror":"https://ror.org/05gt1vc06","country_code":"US","type":"education","lineage":["https://openalex.org/I137853757"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danda B. Rawat","raw_affiliation_strings":["Howard University,Dept. of Electrical Engineering & Computer Science,Washington, DC,USA"],"affiliations":[{"raw_affiliation_string":"Howard University,Dept. of Electrical Engineering & Computer Science,Washington, DC,USA","institution_ids":["https://openalex.org/I137853757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100589865"],"corresponding_institution_ids":["https://openalex.org/I137853757"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70813367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5220","last_page":"5224"},"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":0.9961000084877014,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8333281874656677},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.773654043674469},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7658077478408813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6757796406745911},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4649770259857178},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38403916358947754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38098791241645813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18798324465751648},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1352008581161499},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.061572641134262085},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.055700838565826416}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8333281874656677},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.773654043674469},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7658077478408813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757796406745911},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4649770259857178},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38403916358947754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38098791241645813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18798324465751648},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1352008581161499},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.061572641134262085},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.055700838565826416},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10826072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313488","display_name":"Howard University","ror":"https://ror.org/05gt1vc06"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W116068320","https://openalex.org/W1658008008","https://openalex.org/W1994584977","https://openalex.org/W2089947415","https://openalex.org/W2109910161","https://openalex.org/W3195438473","https://openalex.org/W6636881020","https://openalex.org/W6637242042","https://openalex.org/W6713132740","https://openalex.org/W6718212895"],"related_works":["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","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,13],"(DRL)":[3],"has":[4],"shown":[5],"remarkable":[6],"success":[7],"in":[8,30],"tackling":[9,73],"complex":[10,74],"tasks":[11,34,115],"by":[12,48,86],"representations":[14],"directly":[15],"from":[16],"raw":[17],"data.":[18],"However,":[19],"as":[20,60,62],"DRL":[21,70,85,105],"agents":[22],"become":[23],"increasingly":[24],"sophisticated,":[25],"they":[26],"often":[27],"face":[28],"challenges":[29],"adapting":[31],"to":[32,38,80,107,110],"new":[33,114],"or":[35],"environments":[36],"due":[37],"their":[39],"monolithic":[40],"structure.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,55,103],"prove":[46],"that":[47,66],"decomposing":[49],"the":[50,68,82,98],"agent":[51,71,94],"into":[52],"modular":[53,101],"components,":[54],"enable":[56],"more":[57,63],"efficient":[58,64],"adaptation":[59],"well":[61],"than":[65],"of":[67,84,100,123],"singular":[69],"on":[72],"tasks.":[75],"Overall,":[76],"our":[77],"work":[78],"contributes":[79],"advancing":[81],"field":[83],"introducing":[87],"a":[88],"flexible":[89],"and":[90,119,125],"scalable":[91],"framework":[92],"for":[93],"decomposition.":[95],"By":[96],"enabling":[97],"creation":[99],"agents,":[102],"empower":[104],"systems":[106],"efficiently":[108],"adapt":[109],"changing":[111],"environments,":[112],"learn":[113],"with":[116],"minimal":[117],"intervention,":[118],"achieve":[120],"higher":[121],"levels":[122],"performance":[124],"versatility.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}