{"id":"https://openalex.org/W4307323274","doi":"https://doi.org/10.48550/arxiv.2210.13383","title":"Evaluating Long-Term Memory in 3D Mazes","display_name":"Evaluating Long-Term Memory in 3D Mazes","publication_year":2022,"publication_date":"2022-10-24","ids":{"openalex":"https://openalex.org/W4307323274","doi":"https://doi.org/10.48550/arxiv.2210.13383"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.13383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.13383","pdf_url":"https://arxiv.org/pdf/2210.13383","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.13383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086188713","display_name":"Jurgis Pa\u0161ukonis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasukonis, Jurgis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066294254","display_name":"Timothy Lillicrap","orcid":"https://orcid.org/0000-0001-8918-486X","observed_orcids":["https://orcid.org/0000-0001-8918-486X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lillicrap, Timothy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532071","display_name":"Danijar Hafner","orcid":"https://orcid.org/0000-0002-9534-7271","observed_orcids":["https://orcid.org/0000-0002-9534-7271"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hafner, Danijar","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":36,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":9.999999747378752e-05,"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/long-term-memory","display_name":"long-term memory","score":0.9900000095367432},{"id":"https://openalex.org/keywords/reinforcement-learning-benchmarks","display_name":"reinforcement learning benchmarks","score":0.6060000061988831},{"id":"https://openalex.org/keywords/online-reinforcement-learning","display_name":"online reinforcement learning","score":0.6200000047683716},{"id":"https://openalex.org/keywords/maze-navigation","display_name":"maze navigation","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.771631121635437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726390540599823},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6268585920333862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5331156849861145},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5222245454788208},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48603516817092896},{"id":"https://openalex.org/C179226034","wikidata":"https://www.wikidata.org/wiki/Q18599","display_name":"Short-term memory","level":4,"score":0.4566979706287384},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.41612571477890015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41335344314575195},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.2798936665058136},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.24786260724067688},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23015287518501282},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1912841498851776},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.1129312813282013},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.08558574318885803},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.13383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.13383","pdf_url":"https://arxiv.org/pdf/2210.13383","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.2210.13383","doi":"https://doi.org/10.48550/arxiv.2210.13383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.13383","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.13383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.13383","pdf_url":"https://arxiv.org/pdf/2210.13383","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":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307323274.pdf","grobid_xml":"https://content.openalex.org/works/W4307323274.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2158782408","https://openalex.org/W2781585732","https://openalex.org/W2786036274","https://openalex.org/W2795843265","https://openalex.org/W2900152462","https://openalex.org/W2970364795","https://openalex.org/W2970567787","https://openalex.org/W2973379954","https://openalex.org/W2981030070","https://openalex.org/W2989847975","https://openalex.org/W3005680577","https://openalex.org/W3036619998","https://openalex.org/W3091507139","https://openalex.org/W3201036908","https://openalex.org/W4221146510","https://openalex.org/W4221155677","https://openalex.org/W4283721947","https://openalex.org/W4297808394","https://openalex.org/W4394652010"],"related_works":["https://openalex.org/W7130567193","https://openalex.org/W7161017814","https://openalex.org/W4407683723","https://openalex.org/W7155351437","https://openalex.org/W7171826765","https://openalex.org/W7214043592","https://openalex.org/W7125754759","https://openalex.org/W7223005751","https://openalex.org/W2594903727","https://openalex.org/W7163684479"],"abstract_inverted_index":{"Intelligent":[0],"agents":[1,14,39],"need":[2,40,150],"to":[3,7,34,41,112,151,202],"remember":[4,20,42],"salient":[5],"information":[6,117],"reason":[8],"in":[9,55,63,68,93,160],"partially-observed":[10],"environments.":[11],"For":[12],"example,":[13],"with":[15,176],"a":[16,81,130,140,144],"first-person":[17],"view":[18],"should":[19],"the":[21,43,78,110,149,193,206],"positions":[22],"of":[23,31,46,84,189],"relevant":[24],"objects":[25],"even":[26],"if":[27],"they":[28],"go":[29],"out":[30],"view.":[32],"Similarly,":[33],"effectively":[35],"navigate":[36],"through":[37,179],"rooms":[38,48],"floor":[44],"plan":[45],"how":[47],"are":[49],"connected.":[50],"However,":[51],"most":[52],"benchmark":[53],"tasks":[54],"reinforcement":[56,127],"learning":[57,128],"do":[58],"not":[59],"test":[60],"long-term":[61,91,101],"memory":[62,92,102],"agents,":[64],"slowing":[65],"down":[66],"progress":[67],"this":[69,74],"important":[70],"research":[71],"direction.":[72],"In":[73],"paper,":[75],"we":[76,123],"introduce":[77],"Memory":[79,98,121,207],"Maze,":[80,122],"3D":[82],"domain":[83],"randomized":[85],"mazes":[86],"specifically":[87],"designed":[88],"for":[89,198],"evaluating":[90],"agents.":[94],"Unlike":[95],"existing":[96],"benchmarks,":[97],"Maze":[99],"measures":[100],"separate":[103],"from":[104,174],"confounding":[105],"agent":[106,111],"abilities":[107],"and":[108,134,147,154,181],"requires":[109],"localize":[113],"itself":[114],"by":[115],"integrating":[116],"over":[118],"time.":[119],"With":[120],"propose":[124],"an":[125,135],"online":[126],"benchmark,":[129],"diverse":[131],"offline":[132,136],"dataset,":[133],"probing":[137],"evaluation.":[138],"Recording":[139],"human":[141,190],"player":[142],"establishes":[143],"strong":[145],"baseline":[146],"verifies":[148],"build":[152],"up":[153],"retain":[155],"memories,":[156],"which":[157],"is":[158],"reflected":[159],"their":[161],"gradually":[162],"increasing":[163],"rewards":[164],"within":[165],"each":[166],"episode.":[167],"We":[168],"find":[169],"that":[170],"current":[171],"algorithms":[172],"benefit":[173],"training":[175],"truncated":[177],"backpropagation":[178],"time":[180],"succeed":[182],"on":[183,192,205],"small":[184],"mazes,":[185,195],"but":[186],"fall":[187],"short":[188],"performance":[191],"large":[194],"leaving":[196],"room":[197],"future":[199],"algorithmic":[200],"designs":[201],"be":[203],"evaluated":[204],"Maze.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-10-31T00:00:00"}