{"id":"https://openalex.org/W2590567779","doi":null,"title":"Online Multi-Task Learning Using Biased Sampling","display_name":"Online Multi-Task Learning Using Biased Sampling","publication_year":2017,"publication_date":"2017-02-20","ids":{"openalex":"https://openalex.org/W2590567779","mag":"2590567779"},"language":"en","primary_location":{"id":"mag:2590567779","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1702.06053","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1702.06053","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024150368","display_name":"Sahil Sharma","orcid":"https://orcid.org/0000-0002-3187-4929","observed_orcids":["https://orcid.org/0000-0002-3187-4929"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahil Sharma","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3187-4929","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009374923","display_name":"Balaraman Ravindran","orcid":"https://orcid.org/0000-0002-5364-7639","observed_orcids":["https://orcid.org/0000-0002-5364-7639"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balaraman Ravindran","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5364-7639","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":false,"cited_by_count":1,"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":0.9937000274658203,"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":0.9937000274658203,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004000000189989805,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biased-sampling","display_name":"biased sampling","score":0.7699999809265137},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.9200000166893005},{"id":"https://openalex.org/keywords/goal-directed-behavior","display_name":"goal-directed behavior","score":0.7630000114440918},{"id":"https://openalex.org/keywords/meta-learning","display_name":"meta-learning","score":0.49900001287460327},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.9779999852180481},{"id":"https://openalex.org/keywords/actor-critic","display_name":"actor-critic","score":0.8740000128746033},{"id":"https://openalex.org/keywords/atari-2600","display_name":"Atari 2600","score":0.9589999914169312},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.34200000762939453},{"id":"https://openalex.org/keywords/distillation","display_name":"distillation","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090855479240417},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7238283157348633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6852243542671204},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6733534336090088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6310973167419434},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6286944150924683},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.43535685539245605},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42332160472869873},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2590567779","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1702.06053","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2590567779","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1702.06053","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2680401079","https://openalex.org/W2593765977","https://openalex.org/W2398490066","https://openalex.org/W4415593451","https://openalex.org/W2294276948","https://openalex.org/W3208761439","https://openalex.org/W4394597766","https://openalex.org/W2891076394","https://openalex.org/W7100461424","https://openalex.org/W2523559946"],"abstract_inverted_index":{"One":[0],"of":[1,37,56,158],"the":[2,35,53,57,68,108,125,130,156,160,176,193,201],"long-standing":[3],"challenges":[4],"in":[5,25,34,103,200],"Artificial":[6],"Intelligence":[7],"for":[8,28,86,110,191],"learning":[9,27,40,70,96,117,122],"goal-directed":[10,29,101],"behavior":[11],"is":[12],"to":[13,67,119,163],"build":[14],"a":[15,42,64,167,181],"single":[16],"agent":[17],"which":[18,79,98,154],"can":[19],"solve":[20],"multiple":[21,47,100],"tasks.":[22],"Recent":[23],"progress":[24],"multi-task":[26,69,95,121],"sequential":[30],"problems":[31],"has":[32],"been":[33],"form":[36],"distillation":[38],"based":[39],"wherein":[41],"student":[43],"network":[44],"learns":[45],"from":[46,75],"task-specific":[48,54],"expert":[49,58,77,111],"networks":[50,78],"by":[51,123],"mimicking":[52],"policies":[55],"networks.":[59],"While":[60],"such":[61],"approaches":[62],"offer":[63],"promising":[65],"solution":[66],"problem,":[71],"they":[72],"require":[73,80],"supervision":[74],"large":[76],"extensive":[81],"data":[82],"and":[83,186,218],"computation":[84],"time":[85],"training.":[87],"In":[88],"this":[89],"work,":[90],"we":[91],"propose":[92,134],"an":[93,104],"efficient":[94],"framework":[97],"solves":[99],"tasks":[102,127],"on-line":[105],"setup":[106],"without":[107],"need":[109],"supervision.":[112],"Our":[113],"work":[114],"uses":[115,187],"active":[116,140],"principles":[118],"achieve":[120],"sampling":[124,141],"harder":[126],"more":[128],"than":[129],"easier":[131],"ones.":[132],"We":[133,197],"three":[135,209],"distinct":[136],"models":[137],"under":[138],"our":[139],"framework.":[142],"An":[143],"adaptive":[144],"method":[145,173],"with":[146],"extremely":[147],"competitive":[148],"multi-tasking":[149,194,207],"performance.":[150],"A":[151,171],"UCB-based":[152],"meta-learner":[153],"casts":[155,175],"problem":[157,179,185],"picking":[159,178],"next":[161],"task":[162],"train":[164],"on":[165,205],"as":[166,180],"multi-armed":[168],"bandit":[169],"problem.":[170],"meta-learning":[172],"that":[174],"next-task":[177],"full":[182],"Reinforcement":[183],"Learning":[184],"actor":[188],"critic":[189],"methods":[190],"optimizing":[192],"performance":[195],"directly.":[196],"demonstrate":[198],"results":[199],"Atari":[202],"2600":[203],"domain":[204],"seven":[206],"instances:":[208],"6-task":[210],"instances,":[211],"one":[212,219],"8-task":[213],"instance,":[214],"two":[215],"12-task":[216],"instances":[217],"21-task":[220],"instance.":[221]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-10-03T13:16:28.481748","created_date":"2017-03-03T00:00:00"}