{"id":"https://openalex.org/W4312582031","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892973","title":"Prioritized Sampling with Intrinsic Motivation in Multi-Task Reinforcement Learning","display_name":"Prioritized Sampling with Intrinsic Motivation in Multi-Task Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312582031","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892973"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892973","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063752250","display_name":"Carlo D\u2019Eramo","orcid":"https://orcid.org/0000-0003-2712-118X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Carlo D'Eramo","raw_affiliation_strings":["TU Darmstadt,Computer Science Department,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt,Computer Science Department,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgia Chalvatzaki","raw_affiliation_strings":["TU Darmstadt,Computer Science Department,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"TU Darmstadt,Computer Science Department,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063752250"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.316,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5295022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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":0.8153790831565857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7066083550453186},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6948177814483643},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.668408215045929},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.57695472240448},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47682517766952515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4100785255432129},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32959336042404175},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19274064898490906},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11574971675872803},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09290549159049988},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.05915156006813049}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8153790831565857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7066083550453186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6948177814483643},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.668408215045929},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.57695472240448},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47682517766952515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4100785255432129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32959336042404175},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19274064898490906},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11574971675872803},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09290549159049988},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.05915156006813049},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892973","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1771410628","https://openalex.org/W1863227302","https://openalex.org/W1969074599","https://openalex.org/W1980516134","https://openalex.org/W2004303440","https://openalex.org/W2101524054","https://openalex.org/W2119567691","https://openalex.org/W2120346334","https://openalex.org/W2132622533","https://openalex.org/W2145339207","https://openalex.org/W2168405694","https://openalex.org/W2169619645","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2401657790","https://openalex.org/W2460675832","https://openalex.org/W2565678376","https://openalex.org/W2586680856","https://openalex.org/W2735995851","https://openalex.org/W2739678353","https://openalex.org/W2746553466","https://openalex.org/W2772709170","https://openalex.org/W2781726626","https://openalex.org/W2786928559","https://openalex.org/W2891076394","https://openalex.org/W2913340405","https://openalex.org/W2919115771","https://openalex.org/W2944804155","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2995481444","https://openalex.org/W2998544442","https://openalex.org/W3013821552","https://openalex.org/W3177828909","https://openalex.org/W4214717370","https://openalex.org/W4287329474","https://openalex.org/W4293579911","https://openalex.org/W4297795006","https://openalex.org/W4298174377","https://openalex.org/W6607097208","https://openalex.org/W6638018090","https://openalex.org/W6677737365","https://openalex.org/W6679365036","https://openalex.org/W6684921986","https://openalex.org/W6685043521","https://openalex.org/W6685726866","https://openalex.org/W6687681856","https://openalex.org/W6717230150","https://openalex.org/W6732837357","https://openalex.org/W6740072298","https://openalex.org/W6740879895","https://openalex.org/W6746177919","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6762868464","https://openalex.org/W6762896552","https://openalex.org/W6775647304","https://openalex.org/W6780559895","https://openalex.org/W6790190981"],"related_works":["https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4210912933","https://openalex.org/W2047937115","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2381453893","https://openalex.org/W2379016603","https://openalex.org/W2150361539"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"promises":[4],"to":[5,123,132,191],"lead":[6],"the":[7,11,19,33,51,56,69,87,99,109,127,130,133,136,143,149,156,159,209,212],"next":[8],"advances":[9],"towards":[10],"development":[12],"of":[13,23,35,40,58,61,72,83,89,111,113,120,135,145,158,167],"coveted":[14],"future":[15],"intelligent":[16],"agents.":[17],"However,":[18],"unprecedented":[20],"representational":[21],"power":[22],"deep":[24,28,43,64],"function":[25],"approximators,":[26],"e.g.":[27],"neural":[29],"networks,":[30],"comes":[31],"at":[32],"cost":[34],"demanding":[36],"a":[37,94],"huge":[38],"amount":[39],"experience,":[41],"making":[42,59],"RL":[44,65,91,178],"impractical":[45],"for":[46,147,181],"applications":[47],"requiring":[48],"interactions":[49],"with":[50,93],"real":[52],"world.":[53],"We":[54,194],"study":[55],"problem":[57],"use":[60],"samples":[62],"in":[63,163,215],"more":[66,216],"efficiently,":[67],"exploiting":[68],"desirable":[70],"properties":[71],"knowledge":[73],"generalization":[74],"resulting":[75,162],"from":[76,126],"learning":[77,121,134,144,157],"multiple":[78],"tasks":[79,128,146,202],"together.":[80],"The":[81],"outcome":[82],"our":[84,183,197],"work":[85],"is":[86,151,171],"coupling":[88],"multi-task":[90],"algorithms":[92],"task-sampling":[95],"policy":[96],"based":[97,203],"on":[98,108,176,199,204],"well-known":[100,177],"intrinsic":[101],"motivation":[102],"paradigm.":[103],"In":[104],"particular,":[105],"we":[106],"leverage":[107],"notion":[110],"TD-error":[112],"Bellman":[114],"updates,":[115],"as":[116],"an":[117,164],"effective":[118],"measure":[119],"progress,":[122,153],"prioritize":[124],"sampling":[125,139],"contributing":[129],"most":[131],"agent.":[137],"This":[138],"strategy":[140],"speeds":[141],"up":[142],"which":[148,182],"agent":[150],"showing":[152],"and":[154,188],"postpones":[155],"remaining":[160],"ones,":[161],"optimized":[165],"collection":[166],"samples.":[168],"Our":[169],"method":[170],"supported":[172],"by":[173],"experimental":[174],"evaluations":[175],"control":[179,201],"tasks,":[180],"approach":[184,198],"shows":[185],"superior":[186],"sample-efficiency":[187],"performance":[189],"compared":[190],"representative":[192],"baselines.":[193],"eventually":[195],"evaluate":[196],"simulated":[200],"Quanser":[205],"robotics":[206],"systems,":[207],"confirming":[208],"advantages":[210],"over":[211],"baselines":[213],"also":[214],"realistic":[217],"applications.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-01T06:05:34.837733","created_date":"2025-10-10T00:00:00"}