{"id":"https://openalex.org/W7214099306","doi":"https://doi.org/10.48550/arxiv.2609.25757","title":"Minimal Recurrent Behavioral Memory for Imitation under Partial Observability","display_name":"Minimal Recurrent Behavioral Memory for Imitation under Partial Observability","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214099306","doi":"https://doi.org/10.48550/arxiv.2609.25757"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.25757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25757","pdf_url":"https://arxiv.org/pdf/2609.25757","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/2609.25757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025317164","display_name":"Xianyao Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xianyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152533885","display_name":"Fang Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152521078","display_name":"Rui Min","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111169564","display_name":"Ruitong Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Ruitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5152535155","display_name":"Jing Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Jing","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":0,"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":0.9761000275611877,"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":0.9761000275611877,"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":0.005200000014156103,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-memory","display_name":"recurrent memory","score":0.781000018119812},{"id":"https://openalex.org/keywords/behavioral-imitation","display_name":"behavioral imitation","score":0.6449999809265137},{"id":"https://openalex.org/keywords/partial-observability","display_name":"partial observability","score":0.9950000047683716},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"conditional entropy","score":0.8619999885559082},{"id":"https://openalex.org/keywords/compatibility-relations","display_name":"compatibility relations","score":0.6439999938011169},{"id":"https://openalex.org/keywords/behavioral-models","display_name":"behavioral models","score":0.39100000262260437},{"id":"https://openalex.org/keywords/code-rate","display_name":"code rate","score":0.46299999952316284},{"id":"https://openalex.org/keywords/memory-minimization","display_name":"memory minimization","score":0.33399999141693115},{"id":"https://openalex.org/keywords/reinforcement-learning-from-demonstration","display_name":"reinforcement learning from demonstration","score":0.42800000309944153},{"id":"https://openalex.org/keywords/information-theoretic-limits","display_name":"information-theoretic limits","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7910000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5615000128746033},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4657999873161316},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.3849000036716461},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C78639753","wikidata":"https://www.wikidata.org/wiki/Q3318160","display_name":"Behavioral modeling","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29420000314712524},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.25757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25757","pdf_url":"https://arxiv.org/pdf/2609.25757","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.2609.25757","doi":"https://doi.org/10.48550/arxiv.2609.25757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.25757","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:2609.25757","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25757","pdf_url":"https://arxiv.org/pdf/2609.25757","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214099306.pdf","grobid_xml":"https://content.openalex.org/works/W7214099306.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1686946872","https://openalex.org/W2146778221","https://openalex.org/W2552679343","https://openalex.org/W3175254947","https://openalex.org/W4395444212","https://openalex.org/W4402704519","https://openalex.org/W7133335478","https://openalex.org/W7140159623","https://openalex.org/W7155207192","https://openalex.org/W7160891563","https://openalex.org/W7164163674","https://openalex.org/W7164914702","https://openalex.org/W7165139450","https://openalex.org/W7165613044","https://openalex.org/W7165666711","https://openalex.org/W7165903774","https://openalex.org/W7171787245","https://openalex.org/W7204202063"],"related_works":["https://openalex.org/W2731336219","https://openalex.org/W2038300295","https://openalex.org/W4308484547","https://openalex.org/W3006409079","https://openalex.org/W2925253537","https://openalex.org/W1506712184","https://openalex.org/W7111373479","https://openalex.org/W181513341","https://openalex.org/W3147323166","https://openalex.org/W3135780226"],"abstract_inverted_index":{"What":[0],"is":[1,18,64],"the":[2,19,23,57,61,103,109,161,182,213,217],"least":[3],"recurrent":[4,45],"memory":[5,47,96,132],"needed":[6],"to":[7,102,128,167,176,219],"reproduce":[8],"a":[9,49,134],"specified":[10],"expert":[11],"under":[12,52,108],"partial":[13],"observability?":[14],"The":[15,193],"instantaneous":[16,139],"requirement":[17,136],"conditional":[20],"entropy":[21,66],"of":[22],"expert's":[24],"behavioral":[25,46,84,106],"quotient,":[26],"but":[27,197],"recurrence":[28],"must":[29],"also":[30],"preserve":[31],"distinctions":[32],"that":[33,210],"future":[34],"observations":[35,93],"will":[36],"not":[37],"restore":[38],"before":[39],"use.":[40],"We":[41],"characterize":[42],"this":[43,144],"minimal":[44],"by":[48,92],"compatibility":[50],"relation:":[51],"transitivity":[53],"its":[54],"classes":[55],"attain":[56],"exact":[58,74],"minimum,":[59],"while":[60],"general":[62],"case":[63],"an":[65],"minimization":[67],"over":[68],"closed":[69],"compatible":[70],"state":[71],"assignments,":[72],"with":[73,155],"certificates":[75],"on":[76],"finite":[77],"instances.":[78],"A":[79],"sole-carrier":[80],"measurement":[81],"protocol":[82,183],"separates":[83],"sufficiency,":[85],"excess":[86],"code":[87,116],"rate,":[88],"and":[89,121,130,159,206],"information":[90],"carried":[91],"or":[94],"other":[95],"paths;":[97],"experimental":[98],"bit":[99],"requirements":[100,123],"refer":[101],"induced":[104],"symbolic":[105],"model":[107],"stated":[110],"occupancy.":[111],"Across":[112],"manipulation":[113],"tasks,":[114],"learned":[115],"rates":[117],"remain":[118],"near":[119],"zero-":[120],"two-bit":[122],"as":[124],"hidden":[125],"modes":[126],"grow":[127],"$512$,":[129],"anticipatory":[131],"follows":[133],"$2\\to1\\to0$":[135],"despite":[137],"zero":[138],"demand":[140],"during":[141],"waiting.":[142],"Learning":[143],"representation":[145],"remains":[146],"difficult:":[147],"event-agnostic":[148],"future-behavior":[149],"supervision":[150,194],"yields":[151],"$36/40$":[152],"sufficient":[153,169,188],"seeds":[154,171],"one":[156],"frozen":[157],"configuration":[158],"improves":[160],"longest-horizon":[162],"pixel":[163],"setting":[164],"from":[165,174,216],"$0/8$":[166],"$6/8$":[168],"held-out":[170],"(closed-loop":[172],"success":[173],"$0.08$":[175],"$0.57$).":[177],"On":[178],"unmodified":[179],"community":[180],"benchmarks,":[181],"certifies":[184],"delay-independent":[185],"requirements,":[186],"which":[187],"codes":[189],"match":[190],"at":[191],"mid-delay.":[192],"aids":[195],"commitment":[196],"can":[198],"induce":[199],"predictive":[200],"surplus;":[201],"annealing":[202],"it":[203],"lets":[204],"imitation":[205],"rate":[207],"training":[208],"reduce":[209],"surplus,":[211],"separating":[212],"information-theoretic":[214],"target":[215],"ability":[218],"learn":[220],"it.":[221]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-24T00:00:00"}