{"id":"https://openalex.org/W3157870065","doi":"https://doi.org/10.1145/3412841.3441953","title":"Multi-agent reinforcement learning with directed exploration and selective memory reuse","display_name":"Multi-agent reinforcement learning with directed exploration and selective memory reuse","publication_year":2021,"publication_date":"2021-03-22","ids":{"openalex":"https://openalex.org/W3157870065","doi":"https://doi.org/10.1145/3412841.3441953","mag":"3157870065"},"language":"en","primary_location":{"id":"doi:10.1145/3412841.3441953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3412841.3441953","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3412841.3441953","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3412841.3441953","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015182469","display_name":"Shuo Jiang","orcid":"https://orcid.org/0000-0002-9883-1886"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Shuo Jiang","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033129735","display_name":"Christopher Amato","orcid":"https://orcid.org/0000-0002-6786-7384"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Christopher Amato","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9591,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88453156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"777","last_page":"784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9768000245094299,"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":0.9585000276565552,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9058272838592529},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.831501841545105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7232617139816284},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6726627349853516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4282345771789551},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4274336099624634},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41579484939575195},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13370275497436523},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08408230543136597}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9058272838592529},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.831501841545105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232617139816284},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6726627349853516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4282345771789551},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4274336099624634},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41579484939575195},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13370275497436523},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08408230543136597},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3412841.3441953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3412841.3441953","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3412841.3441953","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3412841.3441953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3412841.3441953","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3412841.3441953","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G4071884661","display_name":null,"funder_award_id":"FA8750-18-S-7007","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157870065.pdf","grobid_xml":"https://content.openalex.org/works/W3157870065.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1757796397","https://openalex.org/W1819447595","https://openalex.org/W2089434629","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2137226992","https://openalex.org/W2145339207","https://openalex.org/W2419612459","https://openalex.org/W2434014514","https://openalex.org/W2507573968","https://openalex.org/W2561776174","https://openalex.org/W2614839826","https://openalex.org/W2623431351","https://openalex.org/W2747213132","https://openalex.org/W2747329762","https://openalex.org/W2775482448","https://openalex.org/W2798511001","https://openalex.org/W2807741983","https://openalex.org/W2913343212","https://openalex.org/W2913668833","https://openalex.org/W2946764808","https://openalex.org/W2950240244","https://openalex.org/W2950794298","https://openalex.org/W2951896791","https://openalex.org/W2962938168","https://openalex.org/W2963523627","https://openalex.org/W2964062135","https://openalex.org/W2996549507"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W1495126611","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W2379533788","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W1853785581","https://openalex.org/W2904106049"],"abstract_inverted_index":{"Many":[0],"tasks":[1],"require":[2],"cooperation":[3],"and":[4,22,45,77,79,93,106],"coordination":[5],"of":[6,57],"multiple":[7],"agents.":[8],"Multi-agent":[9],"reinforcement":[10],"learning":[11],"(MARL)":[12],"can":[13],"effectively":[14],"learn":[15],"solutions":[16],"to":[17,73,89],"these":[18,53],"problems,":[19],"but":[20],"exploration":[21,44,67],"local":[23],"optima":[24],"problems":[25],"are":[26],"still":[27],"open":[28],"research":[29],"topics.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"a":[36,81],"new":[37],"multi-agent":[38],"policy":[39,48,63],"gradient":[40,49],"method":[41,103],"called":[42],"decentralized":[43],"selective":[46,82],"memory":[47,83],"(DecESPG)":[50],"that":[51,70,85,100],"addresses":[52],"issues.":[54],"DecESPG":[55],"consists":[56],"two":[58],"additional":[59],"components":[60],"built":[61],"on":[62],"gradient:":[64],"1)":[65],"an":[66],"bonus":[68],"component":[69,84],"directs":[71],"agents":[72],"explore":[74],"novel":[75],"observations":[76],"actions":[78],"2)":[80],"records":[86],"past":[87],"trajectories":[88],"reuse":[90],"valuable":[91],"experience":[92],"reinforce":[94],"cooperative":[95],"behavior.":[96],"Experimental":[97],"results":[98],"verify":[99],"the":[101],"proposed":[102],"learns":[104],"faster":[105],"outperforms":[107],"state-of-the-art":[108],"MARL":[109],"algorithms.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
