{"id":"https://openalex.org/W4389911035","doi":"https://doi.org/10.48550/arxiv.2107.01460","title":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","display_name":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","publication_year":2021,"publication_date":"2021-07-03","ids":{"openalex":"https://openalex.org/W4389911035","doi":"https://doi.org/10.48550/arxiv.2107.01460"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2107.01460","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.01460","pdf_url":"https://arxiv.org/pdf/2107.01460","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/2107.01460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037797948","display_name":"Ruan John de Kock","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"de Kock, Ruan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016637916","display_name":"Omayma Mahjoub","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahjoub, Omayma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036841115","display_name":"Sasha Abramowitz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abramowitz, Sasha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093510011","display_name":"Wiem Khlifi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khlifi, Wiem","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035164913","display_name":"Callum Rhys Tilbury","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tilbury, Callum Rhys","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074848899","display_name":"Claude Formanek","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Formanek, Claude","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046370375","display_name":"Andries Smit","orcid":"https://orcid.org/0000-0003-2796-5497","observed_orcids":["https://orcid.org/0000-0003-2796-5497"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smit, Andries","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017043594","display_name":"Arnu Pretorius","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pretorius, Arnu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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":0.8949999809265137},{"id":"https://openalex.org/keywords/jax","display_name":"JAX","score":0.9610000252723694},{"id":"https://openalex.org/keywords/distributed-training","display_name":"distributed training","score":0.7689999938011169},{"id":"https://openalex.org/keywords/training-speed","display_name":"training speed","score":0.4519999921321869},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.5339999794960022}],"concepts":[{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.7688331604003906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525256872177124},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7514545917510986},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6603022217750549},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5705353021621704},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5702584385871887},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5493462085723877},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4895089864730835},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.47228580713272095},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.38083788752555847},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3292023837566376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30573680996894836},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1573229730129242},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0874515175819397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07461115717887878},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2107.01460","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.01460","pdf_url":"https://arxiv.org/pdf/2107.01460","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.2107.01460","doi":"https://doi.org/10.48550/arxiv.2107.01460","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.01460","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.01460","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.01460","pdf_url":"https://arxiv.org/pdf/2107.01460","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3179088773","https://openalex.org/W7124257750","https://openalex.org/W4361188839","https://openalex.org/W4307416208","https://openalex.org/W4386806273","https://openalex.org/W4389363807","https://openalex.org/W7081972261","https://openalex.org/W7132275626","https://openalex.org/W4403742889","https://openalex.org/W4384210128"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"research":[4,112,202,220],"is":[5,11,69,229],"inherently":[6],"computationally":[7],"expensive":[8],"and":[9,25,39,90,130,135,139,212,217],"it":[10,55,71],"often":[12],"difficult":[13,52],"to":[14,22,43,57,76,78,93,122,159,172,198],"obtain":[15],"a":[16,51,98,111,142,176],"sufficient":[17],"number":[18],"of":[19,48,101,133,144,156,180,187,190],"experiment":[20],"samples":[21],"test":[23,94,173],"hypotheses":[24],"make":[26],"robust":[27,219],"statistical":[28],"claims.":[29],"Furthermore,":[30],"MARL":[31,49,115,162],"algorithms":[32],"are":[33],"typically":[34],"complex":[35],"in":[36,97,118,175,203,221],"their":[37],"design":[38,129],"can":[40],"be":[41,73,88],"tricky":[42],"implement":[44,79],"correctly.":[45],"These":[46],"aspects":[47],"present":[50],"challenge":[53],"when":[54],"comes":[56],"creating":[58],"useful":[59],"software":[60,68],"for":[61,66,114,170,227],"advanced":[62,201],"research.":[63],"Our":[64],"criteria":[65],"such":[67],"that":[70,120,192],"should":[72],"simple":[74],"enough":[75,92],"use":[77,138],"new":[80],"ideas":[81,96,174],"quickly,":[82],"while":[83,164],"at":[84,231],"the":[85,128,210,222],"same":[86],"time":[87],"scalable":[89],"fast":[91],"those":[95],"reasonable":[99],"amount":[100],"time.":[102],"In":[103,146],"this":[104],"preliminary":[105],"technical":[106],"report,":[107],"we":[108,148],"introduce":[109],"Mava,":[110,134],"library":[113],"written":[116],"purely":[117],"JAX,":[119],"aims":[121],"fulfill":[123],"these":[124],"criteria.":[125],"We":[126,205],"discuss":[127],"core":[131],"features":[132],"demonstrate":[136],"its":[137],"performance":[140],"across":[141],"variety":[143],"environments.":[145],"particular,":[147],"show":[149],"Mava's":[150],"substantial":[151],"speed":[152],"advantage,":[153],"with":[154,195],"improvements":[155],"10-100x":[157],"compared":[158],"other":[160,197],"popular":[161],"frameworks,":[163],"maintaining":[165],"strong":[166],"performance.":[167],"This":[168],"allows":[169],"researchers":[171],"few":[177],"minutes":[178],"instead":[179],"several":[181],"hours.":[182],"Finally,":[183],"Mava":[184,207,228],"forms":[185],"part":[186],"an":[188],"ecosystem":[189],"libraries":[191],"seamlessly":[193],"integrate":[194],"each":[196],"help":[199,213],"facilitate":[200],"MARL.":[204],"hope":[206],"will":[208],"benefit":[209],"community":[211],"drive":[214],"scientifically":[215],"sound":[216],"statistically":[218],"field.":[223],"The":[224],"open-source":[225],"repository":[226],"available":[230],"https://github.com/instadeepai/Mava.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2023-12-19T00:00:00"}