{"id":"https://openalex.org/W4388328811","doi":"https://doi.org/10.48550/arxiv.2311.00865","title":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning","display_name":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W4388328811","doi":"https://doi.org/10.48550/arxiv.2311.00865"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.00865","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00865","pdf_url":"https://arxiv.org/pdf/2311.00865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.00865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062440568","display_name":"Matthias Gerstgrasser","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerstgrasser, Matthias","raw_affiliation_strings":["Computer Science Department , Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department , Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092127564","display_name":"Tom Danino","orcid":"https://orcid.org/0009-0006-0503-6063","observed_orcids":["https://orcid.org/0009-0006-0503-6063"]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Danino, Tom","raw_affiliation_strings":["The Taub Faculty of Computer Science , Technion -Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Taub Faculty of Computer Science , Technion -Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047553225","display_name":"Sarah Keren","orcid":"https://orcid.org/0000-0001-7211-753X","observed_orcids":["https://orcid.org/0000-0001-7211-753X"]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Keren, Sarah","raw_affiliation_strings":["The Taub Faculty of Computer Science , Technion -Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Taub Faculty of Computer Science , Technion -Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/decentralized-learning","display_name":"decentralized learning","score":0.9589999914169312},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.6570000052452087},{"id":"https://openalex.org/keywords/agent-communication","display_name":"agent communication","score":0.3580000102519989}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.796229362487793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780469536781311},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7145165801048279},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6505695581436157},{"id":"https://openalex.org/C2778156585","wikidata":"https://www.wikidata.org/wiki/Q174053","display_name":"Relay","level":3,"score":0.5562971830368042},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49012741446495056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4545518457889557},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4539851248264313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3709285259246826},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.00865","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00865","pdf_url":"https://arxiv.org/pdf/2311.00865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.00865","doi":"https://doi.org/10.48550/arxiv.2311.00865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.00865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.00865","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00865","pdf_url":"https://arxiv.org/pdf/2311.00865","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388328811.pdf","grobid_xml":"https://content.openalex.org/works/W4388328811.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W3183136280","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W4360995913","https://openalex.org/W4281847915"],"abstract_inverted_index":{"We":[0,70],"present":[1],"a":[2,19,35,64,89,113],"novel":[3],"multi-agent":[4,52,83],"RL":[5,53,84],"approach,":[6],"Selective":[7],"Multi-Agent":[8],"Prioritized":[9],"Experience":[10],"Relay,":[11],"in":[12],"which":[13],"agents":[14,18,43],"share":[15],"with":[16],"other":[17,42,51],"limited":[20,65],"number":[21,37,91],"of":[22,38,92,115,123],"transitions":[23],"they":[24],"observe":[25],"during":[26],"training.":[27],"The":[28],"intuition":[29],"behind":[30],"this":[31,55],"is":[32,110,126],"that":[33,72],"even":[34],"small":[36,90],"relevant":[39,94],"experiences":[40,95,99],"from":[41,106],"could":[44],"help":[45],"each":[46],"agent":[47],"learn.":[48],"Unlike":[49],"many":[50],"algorithms,":[54],"approach":[56,74],"allows":[57],"for":[58],"largely":[59],"decentralized":[60,78],"training,":[61],"requiring":[62],"only":[63,88],"communication":[66],"channel":[67],"between":[68,100],"agents.":[69],"show":[71],"our":[73,124],"outperforms":[75,96],"baseline":[76],"no-sharing":[77],"training":[79],"and":[80,102,117],"state-of-the":[81],"art":[82],"algorithms.":[85],"Further,":[86],"sharing":[87,97,109],"highly":[93],"all":[98],"agents,":[101],"the":[103],"performance":[104],"uplift":[105],"selective":[107],"experience":[108],"robust":[111],"across":[112],"range":[114],"hyperparameters":[116],"DQN":[118],"variants.":[119],"A":[120],"reference":[121],"implementation":[122],"algorithm":[125],"available":[127],"at":[128],"https://github.com/mgerstgrasser/super.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}