{"id":"https://openalex.org/W4401201670","doi":"https://doi.org/10.52202/085713-4437","title":"NAVIX: Scaling MiniGrid Environments with JAX","display_name":"NAVIX: Scaling MiniGrid Environments with JAX","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4401201670","doi":"https://doi.org/10.52202/085713-4437"},"language":"en","primary_location":{"id":"doi:10.52202/085713-4437","doi":"https://doi.org/10.52202/085713-4437","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-4437","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.19396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047676934","display_name":"Eduardo Pignatelli","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eduardo Pignatelli","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099282523","display_name":"Jarek Liesen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jarek Liesen","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013857977","display_name":"Robert Tjarko Lange","orcid":"https://orcid.org/0009-0005-8799-1138","observed_orcids":["https://orcid.org/0009-0005-8799-1138"]},"institutions":[{"id":"https://openalex.org/I4405259418","display_name":"Sakana AI (Japan)","ror":"https://ror.org/027eejh88","country_code":"JP","type":"company","lineage":["https://openalex.org/I4405259418"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE","JP"],"is_corresponding":false,"raw_author_name":"Robert Lange","raw_affiliation_strings":["TU Berlin / Sakana.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Berlin / Sakana.AI","institution_ids":["https://openalex.org/I4405259418","https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chris Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Lu","raw_affiliation_strings":["OpenAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenAI","institution_ids":["https://openalex.org/I4210161460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068291173","display_name":"Pablo Samuel Castro","orcid":"https://orcid.org/0000-0002-3206-336X","observed_orcids":["https://orcid.org/0000-0002-3206-336X"]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pablo Samuel Castro","raw_affiliation_strings":["Google DeepMind / U. de Montreal / Mila"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind / U. de Montreal / Mila","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071335453","display_name":"Laura Toni","orcid":"https://orcid.org/0000-0002-8441-8791","observed_orcids":["https://orcid.org/0000-0002-8441-8791"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laura Toni","raw_affiliation_strings":["UCL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCL","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.1774,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97116305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"147576","last_page":"147608"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minigrid","display_name":"MiniGrid","score":0.9549999833106995},{"id":"https://openalex.org/keywords/jax","display_name":"JAX","score":0.8820000290870667},{"id":"https://openalex.org/keywords/environment-simulation","display_name":"environment simulation","score":0.37700000405311584},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.6069999933242798}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5066445469856262},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32210272550582886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17337143421173096},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06796824932098389}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-4437","doi":"https://doi.org/10.52202/085713-4437","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-4437","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.19396","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19396","pdf_url":"https://arxiv.org/pdf/2407.19396","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.19396","doi":"https://doi.org/10.48550/arxiv.2407.19396","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.19396","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:2407.19396","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19396","pdf_url":"https://arxiv.org/pdf/2407.19396","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401201670.pdf","grobid_xml":"https://content.openalex.org/works/W4401201670.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2920362155","https://openalex.org/W2948937890","https://openalex.org/W3037207827","https://openalex.org/W3113190209","https://openalex.org/W3123725896","https://openalex.org/W3128522352","https://openalex.org/W3201036908","https://openalex.org/W4381252681","https://openalex.org/W4392223126","https://openalex.org/W4399837569","https://openalex.org/W4415797718","https://openalex.org/W7133235596"],"related_works":["https://openalex.org/W4415797730","https://openalex.org/W3196764258","https://openalex.org/W7124257750","https://openalex.org/W2793035934","https://openalex.org/W7133229195","https://openalex.org/W3121702453","https://openalex.org/W4414818929","https://openalex.org/W4381252681","https://openalex.org/W7133223694","https://openalex.org/W7125773115"],"abstract_inverted_index":{"As":[0],"Deep":[1,61],"Reinforcement":[2,83],"Learning":[3,84],"(Deep":[4],"RL)":[5],"research":[6],"moves":[7],"towards":[8],"solving":[9],"large-scale":[10],"worlds,":[11],"efficient":[12],"environment":[13],"simulations":[14],"become":[15,74],"crucial":[16],"for":[17,77],"rapid":[18],"experimentation.":[19],"However,":[20],"most":[21,81],"existing":[22],"environments":[23,72],"struggle":[24],"to":[25,27,47,140,159],"scale":[26],"high":[28],"throughput,":[29,45],"setting":[30],"back":[31],"meaningful":[32],"progress.":[33,78],"Interactions":[34],"are":[35],"typically":[36],"computed":[37],"on":[38,95,145],"the":[39,55,80,90,112],"CPU,":[40],"limiting":[41],"training":[42,63],"speed":[43,133],"and":[44,50,66,70,105,108,166],"due":[46],"slower":[48],"computation":[49],"communication":[51],"overhead":[52],"when":[53],"distributing":[54],"task":[56],"across":[57],"multiple":[58],"machines.":[59],"Ultimately,":[60],"RL":[62,169],"is":[64,88],"CPU-bound,":[65],"developing":[67],"batched,":[68],"fast,":[69],"scalable":[71,168],"has":[73],"a":[75,122,146],"frontier":[76],"Among":[79],"used":[82],"(RL)":[85],"environments,":[86],"MiniGrid":[87,125],"at":[89],"foundation":[91],"of":[92,124],"several":[93],"studies":[94],"exploration,":[96],"curriculum":[97],"learning,":[98,100],"representation":[99],"diversity,":[101],"meta-learning,":[102],"credit":[103],"assignment,":[104],"language-conditioned":[106],"RL,":[107],"still":[109],"suffers":[110],"from":[111,156],"limitations":[113],"described":[114],"above.":[115],"In":[116],"this":[117],"work,":[118],"we":[119],"introduce":[120],"NAVIX,":[121],"re-implementation":[123],"in":[126,135,143],"JAX.":[127],"NAVIX":[128],"achieves":[129],"over":[130],"200":[131],"000x":[132],"improvements":[134],"batch":[136],"mode,":[137],"supporting":[138],"up":[139],"2048":[141],"agents":[142],"parallel":[144],"single":[147],"Nvidia":[148],"A100":[149],"80":[150],"GB.":[151],"This":[152],"reduces":[153],"experiment":[154],"times":[155],"one":[157],"week":[158],"15":[160],"minutes,":[161],"promoting":[162],"faster":[163],"design":[164],"iterations":[165],"more":[167],"model":[170],"development.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-08-01T00:00:00"}