{"id":"https://openalex.org/W2739573821","doi":"https://doi.org/10.3390/make1010002","title":"Learning to Teach Reinforcement Learning Agents","display_name":"Learning to Teach Reinforcement Learning Agents","publication_year":2017,"publication_date":"2017-12-06","ids":{"openalex":"https://openalex.org/W2739573821","doi":"https://doi.org/10.3390/make1010002","mag":"2739573821"},"language":"en","primary_location":{"id":"doi:10.3390/make1010002","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make1010002","pdf_url":"https://www.mdpi.com/2504-4990/1/1/2/pdf?version=1545200511","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/1/1/2/pdf?version=1545200511","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Anestis Fachantidis","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Anestis Fachantidis","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Matthew Taylor","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthew Taylor","raw_affiliation_strings":["Borealis AI, University of Alberta, CCIS 3-232, Edmonton, AB T6G 2M9, Canada"],"affiliations":[{"raw_affiliation_string":"Borealis AI, University of Alberta, CCIS 3-232, Edmonton, AB T6G 2M9, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ioannis Vlahavas","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Vlahavas","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":3.1181,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.93372151,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"21","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6089000105857849,"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":0.6089000105857849,"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":0.09459999948740005,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.05460000038146973,"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":0.7300999760627747},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.6370000243186951},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6187999844551086},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.5745000243186951},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5644999742507935},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5637999773025513},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.4862000048160553}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7300999760627747},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5637999773025513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5475000143051147},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4684999883174896},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.3723999857902527},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.29499998688697815},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/make1010002","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make1010002","pdf_url":"https://www.mdpi.com/2504-4990/1/1/2/pdf?version=1545200511","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1707.09079","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.09079","pdf_url":"https://arxiv.org/pdf/1707.09079","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:mdpi.com:/2504-4990/1/1/2/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/make1010002","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction; Volume 1; Issue 1; Pages: 21-42","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/make1010002","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make1010002","pdf_url":"https://www.mdpi.com/2504-4990/1/1/2/pdf?version=1545200511","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739573821.pdf","grobid_xml":"https://content.openalex.org/works/W2739573821.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W158722652","https://openalex.org/W1460713219","https://openalex.org/W1529399279","https://openalex.org/W1549353711","https://openalex.org/W1589064538","https://openalex.org/W1606056663","https://openalex.org/W1974043469","https://openalex.org/W2012757283","https://openalex.org/W2110292307","https://openalex.org/W2132625905","https://openalex.org/W2141559645","https://openalex.org/W2153353285","https://openalex.org/W2161283668","https://openalex.org/W2620645529","https://openalex.org/W2735506162","https://openalex.org/W4214717370","https://openalex.org/W6674600207","https://openalex.org/W6679818365","https://openalex.org/W6730844258"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,47,189],"article,":[2,190],"we":[3,38,134,191],"study":[4],"the":[5,28,51,55,60,71,77,82,86,106,110,125,136,172],"transfer":[6],"learning":[7,19,114,140,147,151,185,194,207],"model":[8],"of":[9,30,54,62,85,88,150,171,203],"action":[10,22,175],"advice":[11,23,35,44,117,132],"under":[12,32,118,197],"a":[13,33,92,119,139,144,198,204],"budget.":[14,36,120],"We":[15],"focus":[16],"on":[17,129],"reinforcement":[18,146],"teachers":[20,79],"providing":[21],"to":[24,105,153,162,183,195],"heterogeneous":[25],"students":[26],"playing":[27],"game":[29],"Pac-Man":[31],"limited":[34],"First,":[37],"examine":[39],"several":[40],"critical":[41],"factors":[42],"affecting":[43],"quality":[45],"in":[46,65,124,188],"setting,":[48],"such":[49],"as":[50,91,138],"average":[52],"performance":[53],"teacher,":[56],"its":[57],"variance":[58,104],"and":[59,80,142,176],"importance":[61,84],"reward":[63],"discounting":[64],"advising.":[66],"The":[67,100,157],"experiments":[68],"show":[69],"that":[70,97,193],"best":[72,78],"performers":[73],"are":[74],"not":[75,168],"always":[76],"reveal":[81],"non-trivial":[83],"coefficient":[87],"variation":[89],"(CV)":[90],"statistic":[93,102],"for":[94,115,131],"choosing":[95],"policies":[96],"generate":[98],"advice.":[99],"CV":[101],"relates":[103],"corresponding":[107],"mean.":[108],"Second,":[109],"article":[111],"studies":[112],"policy":[113],"distributing":[116],"Whereas":[121],"most":[122],"methods":[123],"relevant":[126],"literature":[127],"rely":[128],"heuristics":[130],"distribution,":[133],"formulate":[135],"problem":[137],"one":[141],"propose":[143],"novel":[145],"algorithm":[148,159],"capable":[149],"when":[152,165],"advise":[154,163,196],"or":[155],"not.":[156],"proposed":[158],"is":[160,200],"able":[161],"even":[164],"it":[166],"does":[167],"have":[169],"knowledge":[170],"student\u2019s":[173],"intended":[174],"needs":[177],"significantly":[178],"less":[179],"training":[180],"time":[181],"compared":[182],"previous":[184],"approaches.":[186],"Finally,":[187],"argue":[192],"budget":[199],"an":[201],"instance":[202],"more":[205],"generic":[206],"problem:":[208],"Constrained":[209],"Exploitation":[210],"Reinforcement":[211],"Learning.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2017-08-08T00:00:00"}