{"id":"https://openalex.org/W3131282405","doi":"https://doi.org/10.13016/2akq-hrp2","title":"Learning with Minimal Supervision: New Meta-Learning and Reinforcement Learning Algorithms","display_name":"Learning with Minimal Supervision: New Meta-Learning and Reinforcement Learning Algorithms","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3131282405","doi":"https://doi.org/10.13016/2akq-hrp2","mag":"3131282405"},"language":"en","primary_location":{"id":"mag:3131282405","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/26826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/2akq-hrp2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068614789","display_name":"Amr Sharaf","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sharaf, Amr","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5068614789"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.6456999778747559,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.6456999778747559,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.6273999810218811,"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/T10510","display_name":"Stroke Rehabilitation and Recovery","score":0.5552999973297119,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6860045194625854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5421707034111023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49976038932800293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47562387585639954},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.42764484882354736},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42704248428344727},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4188990890979767},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14935025572776794}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6860045194625854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5421707034111023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49976038932800293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47562387585639954},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.42764484882354736},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42704248428344727},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4188990890979767},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14935025572776794},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:3131282405","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/26826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.13016/2akq-hrp2","is_oa":true,"landing_page_url":"https://doi.org/10.13016/2akq-hrp2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Collection"}],"best_oa_location":{"id":"doi:10.13016/2akq-hrp2","is_oa":true,"landing_page_url":"https://doi.org/10.13016/2akq-hrp2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Collection"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2906146006","https://openalex.org/W3022468183","https://openalex.org/W2924734182","https://openalex.org/W3109381819","https://openalex.org/W2969320674","https://openalex.org/W1538318259","https://openalex.org/W2975874528","https://openalex.org/W2617354312","https://openalex.org/W2972485442","https://openalex.org/W2742132707","https://openalex.org/W3010977789","https://openalex.org/W2149645818","https://openalex.org/W3038202767","https://openalex.org/W2147558615","https://openalex.org/W240282437","https://openalex.org/W2318526480","https://openalex.org/W3108338917","https://openalex.org/W3181692234","https://openalex.org/W2367922714","https://openalex.org/W3207188183"],"abstract_inverted_index":{"Standard":[0],"machine":[1,123],"learning":[2,6,48,58,85,91,96,109,132,141,180,194,206,248,258,261,276,290],"approaches":[3,107],"thrive":[4],"on":[5,88,170,197],"from":[7,34,262],"huge":[8],"amounts":[9,23,70],"of":[10,24,71,101,121,152,189],"labeled":[11,25,167,239],"training":[12,214],"data,":[13,215],"but":[14],"what":[15],"if":[16],"we":[17,63,104,192,255],"don\u2019t":[18],"have":[19,28,209],"access":[20,162,210,223,268,297],"to":[21,32,52,92,133,163,177,211,221,224,236,245,269,298],"large":[22],"datasets?":[26],"Humans":[27],"a":[29,36,165,225,287],"remarkable":[30],"ability":[31],"learn":[33,67,135,295],"only":[35,164],"few":[37,166],"examples.":[38],"To":[39],"do":[40],"so,":[41],"they":[42],"either":[43],"build":[44],"upon":[45],"their":[46],"prior":[47],"experiences,":[49],"or":[50,229],"adapt":[51],"new":[53],"circumstances":[54],"by":[55,74,131],"observing":[56],"sparse":[57,226,264,299],"signals.":[59,301],"In":[60,185,202,281],"this":[61,253],"dissertation,":[62,103,191],"promote":[64],"algorithms":[65,86,117,154,195,259],"that":[66,232,292],"with":[68,110,182],"minimal":[69,111,183],"supervision":[72],"inspired":[73],"these":[75,153,171,247],"two":[76,80],"ideas.":[77],"We":[78,113],"discuss":[79,105],"families":[81],"for":[82,108,118,260],"minimally":[83,288],"supervised":[84,213,289],"based":[87,196],"meta-learning":[89,106,116],"(or":[90],"learn)":[93],"and":[94,140,199,272],"reinforcement":[95,198],"approaches.In":[97],"the":[98,102,146,159,173,186,190,205,238,284],"first":[99],"part":[100,188],"supervision.":[112,184],"present":[114,193,256],"three":[115,257],"few-shot":[119],"adaptation":[120],"neural":[122],"translation":[124],"systems,":[125],"promoting":[126],"fairness":[127,137],"in":[128,145,157],"learned":[129],"models":[130],"actively":[134],"under":[136,278],"parity":[138],"constraints,":[139],"better":[142],"exploration":[143],"policies":[144],"interactive":[147],"contextual":[148],"bandit":[149,279],"setting.":[150],"All":[151],"simulate":[155],"settings":[156,204],"which":[158],"agent":[160,174,207],"has":[161],"samples.":[168],"Based":[169],"simulations,":[172],"learns":[175],"how":[176],"solve":[178],"future":[179],"tasks":[181,277],"second":[187],"imitation":[200],"learning.":[201],"many":[203],"doesn\u2019t":[208],"fully":[212],"however,":[216],"it":[217],"might":[218],"be":[219,234],"able":[220],"leverage":[222],"reward":[227,265,300],"signal,":[228],"an":[230],"expert":[231],"can":[233,293],"queried":[235],"collect":[237],"data.":[240],"It":[241],"is":[242,286],"important":[243],"then":[244],"utilize":[246],"signals":[249],"efficiently.":[250],"Towards":[251],"achieving":[252],"goal,":[254],"very":[263],"signals,":[266],"leveraging":[267],"noisy":[270],"guidance,":[271],"solving":[273],"structured":[274],"prediction":[275],"feedback.":[280],"all":[282],"cases,":[283],"result":[285],"algorithm":[291],"effectively":[294],"given":[296]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}