{"id":"https://openalex.org/W7009813624","doi":null,"title":"Flexible Curriculum Learning for Deep Reinforcement Learning Agents","display_name":"Flexible Curriculum Learning for Deep Reinforcement Learning Agents","publication_year":2018,"publication_date":"2018-11-23","ids":{"openalex":"https://openalex.org/W7009813624"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","pdf_url":"http://resolver.tudelft.nl/uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dorscheidt, Joost (author)","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Dorscheidt, Joost (author)","raw_affiliation_strings":["Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"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":true,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/ddpg","display_name":"deep deterministic policy gradient","score":0.8840000033378601},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.8989999890327454},{"id":"https://openalex.org/keywords/agent-coordination","display_name":"agent coordination","score":0.6050000190734863},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.879800021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6518999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6334999799728394},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37040001153945923},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.2745000123977661},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","pdf_url":"http://resolver.tudelft.nl/uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","pdf_url":"http://resolver.tudelft.nl/uuid:6e220c8b-e5c1-4c68-bf59-1bf0b76ef8fb","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7009813624.pdf","grobid_xml":"https://content.openalex.org/works/W7009813624.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1165382972","https://openalex.org/W1498436455","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W2007347635","https://openalex.org/W2104144149","https://openalex.org/W2112796928","https://openalex.org/W2123981539","https://openalex.org/W2158782408","https://openalex.org/W2163605009","https://openalex.org/W2296073425","https://openalex.org/W2726187156","https://openalex.org/W2781585732","https://openalex.org/W2782014475","https://openalex.org/W4214717370","https://openalex.org/W4231109964","https://openalex.org/W4319988532"],"related_works":["https://openalex.org/W2810758782","https://openalex.org/W6922322361","https://openalex.org/W4408258402","https://openalex.org/W4286503956","https://openalex.org/W3110107275","https://openalex.org/W4205472340","https://openalex.org/W4367060986","https://openalex.org/W3017431598","https://openalex.org/W2952361484","https://openalex.org/W4404570887"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"is":[3,63,75,89,115,126,134,151,158],"a":[4,16,70,76,105,120,129,154,168,173],"learning":[5,61,67,74,108],"paradigm":[6],"that":[7,162],"learns":[8],"by":[9,64],"interacting":[10],"with":[11],"the":[12,44,56,66,81,87,100,141,147,163],"environment.":[13],"In":[14,102,145],"practice,":[15],"RL":[17],"agent":[18,88],"needs":[19],"to":[20,24,95,117,136,172],"perform":[21],"many":[22],"actions":[23],"sample":[25,45,57,170],"rewards":[26],"and":[27],"state":[28,84],"transitions":[29],"from":[30],"their":[31],"environments.":[32,51],"Recent":[33],"advances":[34],"in":[35,47,92,119],"using":[36],"deep":[37,106],"neural":[38],"networks":[39],"as":[40],"function":[41],"approximators":[42],"reduce":[43],"complexity":[46,58,98,171],"very":[48],"high":[49],"dimensional":[50],"Another":[52],"way":[53,77],"of":[54,59,78,86,99,140],"reducing":[55],"reinforcement":[60,107],"agents":[62],"shaping":[65,79],"path":[68],"into":[69],"curriculum.":[71],"Flexible":[72],"curriculum":[73],"where":[80,131,156],"action":[82],"and/or":[83],"dimensionality":[85],"gradually":[90],"increased,":[91],"an":[93],"effort":[94],"slowly":[96],"increase":[97],"problem.":[101],"this":[103],"research,":[104],"architecture,":[109],"Deep":[110],"Deterministic":[111],"Policy":[112],"Gradients":[113],"(DDPG),":[114],"modified":[116],"learn":[118],"flexible":[121,124,142,148,164],"way.":[122],"The":[123],"DDPG":[125,143,149,165],"evaluated":[127,152],"on":[128,153],"problem":[130,155],"no":[132],"coordination":[133,157],"required":[135],"test":[137],"basic":[138],"functionality":[139],"algorithm.":[144],"addition,":[146],"algorithm":[150,166],"required.":[159],"Results":[160],"show":[161],"has":[167],"comparable":[169],"non-flexible":[174],"approach.":[175]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}