{"id":"https://openalex.org/W6969372954","doi":"https://doi.org/10.5555/3635637.3663188","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","display_name":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6969372954","doi":"https://doi.org/10.5555/3635637.3663188"},"language":"en","primary_location":{"id":"pmh:oai:upcommons.upc.edu:2117/421001","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/421001","pdf_url":"https://upcommons.upc.edu/bitstreams/28ef45ab-5d79-4b91-a287-b00e10d79bcb/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstreams/28ef45ab-5d79-4b91-a287-b00e10d79bcb/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rutherford, A","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rutherford, A","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ellis, B","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ellis, B","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gallici, M","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gallici, M","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cook, J","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cook, J","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lupu, A","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lupu, A","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ingvarsson, G","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingvarsson, G","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Willi, T","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Willi, T","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hammond, R","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hammond, R","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Khan, A","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, A","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"de Witt, CS","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"de Witt, CS","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Souly, A","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Souly, A","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bandyopadhyay, S","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bandyopadhyay, S","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Samvelyan, M","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samvelyan, M","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, M","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, M","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lange, R","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lange, R","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Whiteson, S","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Whiteson, S","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lacerda, B","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lacerda, B","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hawes, N","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hawes, N","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rockt\u00e4schel, T","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rockt\u00e4schel, T","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lu, C","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, C","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Foerster, J","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Foerster, J","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":21,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2023,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83927696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.670199990272522,"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":0.670199990272522,"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":0.1941000074148178,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.012299999594688416,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7354999780654907},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.734000027179718},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7099000215530396},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5839999914169312},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5529999732971191},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5304999947547913},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4251999855041504},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4097000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882999777793884},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7354999780654907},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.734000027179718},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7099000215530396},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5645999908447266},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5529999732971191},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35179999470710754},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:upcommons.upc.edu:2117/421001","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/421001","pdf_url":"https://upcommons.upc.edu/bitstreams/28ef45ab-5d79-4b91-a287-b00e10d79bcb/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10216730","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10216730/","pdf_url":"https://discovery.ucl.ac.uk/10216730/1/NeurIPS-2024-jaxmarl-multi-agent-rl-environments-and-algorithms-in-jax-Paper-Datasets_and_Benchmarks_Track.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Globersons, Amir and Mackey, Lester and Belgrave, Danielle and Fan, Angela and Paquet, Ulrich and Tomczak, Jakub M and Zhang, Cheng, (eds.) Advances in Neural Information Processing Systems.    NeurIPS (2024)","raw_type":"Proceedings paper"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:c55e6f68-1e87-43ed-9489-7eb1ac30c728","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/421001","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/421001","pdf_url":"https://upcommons.upc.edu/bitstreams/28ef45ab-5d79-4b91-a287-b00e10d79bcb/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W6969372954.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"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":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-21T07:57:09.225873","created_date":"2025-10-10T00:00:00"}