{"id":"https://openalex.org/W4388788987","doi":"https://doi.org/10.48550/arxiv.2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","display_name":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","publication_year":2023,"publication_date":"2023-11-16","ids":{"openalex":"https://openalex.org/W4388788987","doi":"https://doi.org/10.48550/arxiv.2311.10090"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.10090","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2311.10090","pdf_url":"https://arxiv.org/pdf/2311.10090","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.10090","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067269931","display_name":"Alexander R. Rutherford","orcid":"https://orcid.org/0000-0001-5661-2063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rutherford, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066273738","display_name":"Benjamin J. Ellis","orcid":"https://orcid.org/0000-0001-6897-1303"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ellis, Benjamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008938807","display_name":"Matteo Gallici","orcid":"https://orcid.org/0000-0002-4898-2766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gallici, Matteo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014312938","display_name":"Jonathan Cook","orcid":"https://orcid.org/0000-0003-4907-5719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cook, Jonathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086769710","display_name":"Andrei N. Lupu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lupu, Andrei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084628600","display_name":"Gar\u00f0ar Ingvarsson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingvarsson, Gardar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041285498","display_name":"Timon Willi","orcid":"https://orcid.org/0000-0003-4405-5700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Willi, Timon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hammond, Ravi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hammond, Ravi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084386381","display_name":"Akbir Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Akbir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112436473","display_name":"Christian Schroeder de Witt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"de Witt, Christian Schroeder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004786699","display_name":"Alexandra Souly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Souly, Alexandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039352843","display_name":"Saptarashmi Bandyopadhyay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bandyopadhyay, Saptarashmi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016880022","display_name":"Mikayel Samvelyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samvelyan, Mikayel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017949957","display_name":"Minqi Jiang","orcid":"https://orcid.org/0000-0003-1285-0208"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Minqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013857977","display_name":"Robert Tjarko Lange","orcid":"https://orcid.org/0009-0005-8799-1138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lange, Robert Tjarko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Whiteson, Shimon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053556869","display_name":"Bruno Lacerda","orcid":"https://orcid.org/0000-0003-0862-331X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lacerda, Bruno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059686746","display_name":"Nick Hawes","orcid":"https://orcid.org/0000-0002-7556-6098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hawes, Nick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079315903","display_name":"Tim Rockt\u00e4schel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rocktaschel, Tim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030505775","display_name":"Chris Xiaoxuan Lu","orcid":"https://orcid.org/0000-0002-3733-4480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Chris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059094093","display_name":"Jakob Foerster","orcid":"https://orcid.org/0000-0001-9688-2498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Foerster, Jakob Nicolaus","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":true,"cited_by_count":2,"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":0.9797999858856201,"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":0.9797999858856201,"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":0.9562000036239624,"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/T11197","display_name":"Digital Games and Media","score":0.9312000274658203,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7837511301040649},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7395602464675903},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.699561357498169},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5882653594017029},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.578918993473053},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48101645708084106},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.4711398482322693},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.41816943883895874},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3539328873157501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34395480155944824},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3387277126312256},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.16083499789237976},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13074642419815063},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11941224336624146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837511301040649},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7395602464675903},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.699561357498169},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5882653594017029},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.578918993473053},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48101645708084106},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.4711398482322693},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41816943883895874},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3539328873157501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34395480155944824},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3387277126312256},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.16083499789237976},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13074642419815063},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11941224336624146},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.10090","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2311.10090","pdf_url":"https://arxiv.org/pdf/2311.10090","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.10090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.10090","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.10090","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2311.10090","pdf_url":"https://arxiv.org/pdf/2311.10090","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3381034187","display_name":"SHAIC1: Towards Scalable Human-AI Coordination from First Principles","funder_award_id":"EP/Y028481/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6198381055","display_name":"From Sensing to Collaboration: Engineering, Exploring and Exploiting the Building Blocks of Embodied Intelligence - An EPSRC Programme Grant","funder_award_id":"EP/V000748/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388788987.pdf","grobid_xml":"https://content.openalex.org/works/W4388788987.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2093541819","https://openalex.org/W2032294417","https://openalex.org/W2152754392","https://openalex.org/W1989172970","https://openalex.org/W2196316523","https://openalex.org/W1899363654"],"abstract_inverted_index":{"Benchmarks":[0],"are":[1,134],"crucial":[2],"in":[3,37,108,147,201],"the":[4,24,41,80,144,148,161,168,172,192],"development":[5],"of":[6,44,95,110,160],"machine":[7],"learning":[8,16],"algorithms,":[9],"with":[10,30,89],"available":[11,206],"environments":[12,21,99],"significantly":[13],"influencing":[14],"reinforcement":[15],"(RL)":[17],"research.":[18],"Traditionally,":[19],"RL":[20,50],"run":[22,171],"on":[23],"CPU,":[25],"which":[26,166],"limits":[27],"their":[28],"scalability":[29],"typical":[31],"academic":[32],"compute.":[33],"However,":[34],"recent":[35],"advancements":[36],"JAX":[38],"have":[39],"enabled":[40],"wider":[42],"use":[43],"hardware":[45],"acceleration,":[46,182],"enabling":[47],"massively":[48],"parallel":[49],"training":[51,116,132],"pipelines":[52],"and":[53,100,126,139,153,197],"environments.":[54],"While":[55],"this":[56,75],"has":[57,65],"been":[58,68],"successfully":[59],"applied":[60],"to":[61,128,170],"single-agent":[62],"RL,":[63],"it":[64],"not":[66,178],"yet":[67],"widely":[69],"adopted":[70],"for":[71,91,194],"multi-agent":[72],"scenarios.":[73],"In":[74],"paper,":[76],"we":[77],"present":[78],"JaxMARL,":[79],"first":[81],"open-source,":[82],"Python-based":[83],"library":[84],"that":[85],"combines":[86],"GPU-enabled":[87],"efficiency":[88],"support":[90],"a":[92,156,186],"large":[93],"number":[94],"commonly":[96],"used":[97],"MARL":[98,189],"popular":[101,162],"baseline":[102],"algorithms.":[103],"Our":[104],"experiments":[105],"show":[106],"that,":[107],"terms":[109],"wall":[111],"clock":[112],"time,":[113],"our":[114],"JAX-based":[115,157],"pipeline":[117],"is":[118,205],"around":[119],"14":[120],"times":[121],"faster":[122],"than":[123],"existing":[124],"approaches,":[125],"up":[127],"12500x":[129],"when":[130],"multiple":[131],"runs":[133],"vectorized.":[135],"This":[136,177],"enables":[137,180],"efficient":[138],"thorough":[140],"evaluations,":[141],"potentially":[142],"alleviating":[143],"evaluation":[145],"crisis":[146],"field.":[149],"We":[150],"also":[151,184],"introduce":[152],"benchmark":[154],"SMAX,":[155],"approximate":[158],"reimplementation":[159],"StarCraft":[163,173],"Multi-Agent":[164],"Challenge,":[165],"removes":[167],"need":[169],"II":[174],"game":[175],"engine.":[176],"only":[179],"GPU":[181],"but":[183],"provides":[185],"more":[187],"flexible":[188],"environment,":[190],"unlocking":[191],"potential":[193],"self-play,":[195],"meta-learning,":[196],"other":[198],"future":[199],"applications":[200],"MARL.":[202],"The":[203],"code":[204],"at":[207],"https://github.com/flairox/jaxmarl.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2023-11-18T00:00:00"}