{"id":"https://openalex.org/W2793798239","doi":"https://doi.org/10.1109/tnnls.2018.2790981","title":"Self-Paced Prioritized Curriculum Learning With Coverage Penalty in Deep Reinforcement Learning","display_name":"Self-Paced Prioritized Curriculum Learning With Coverage Penalty in Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-02-01","ids":{"openalex":"https://openalex.org/W2793798239","doi":"https://doi.org/10.1109/tnnls.2018.2790981","mag":"2793798239","pmid":"https://pubmed.ncbi.nlm.nih.gov/29771673"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2790981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2790981","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://unsworks.unsw.edu.au/bitstreams/d7f89b73-44c6-4f9d-ace9-c5e68c1c2c9f/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081583243","display_name":"Zhipeng Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Ren","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000582423","display_name":"Daoyi Dong","orcid":"https://orcid.org/0000-0002-7425-3559"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daoyi Dong","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7425-3559","affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076835782","display_name":"Huaxiong Li","orcid":"https://orcid.org/0000-0003-0395-1525"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxiong Li","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0395-1525","affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3929-4707","affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":9.6411,"has_fulltext":true,"cited_by_count":123,"citation_normalized_percentile":{"value":0.98345763,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"29","issue":"6","first_page":"2216","last_page":"2226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9682999849319458,"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":0.89061039686203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8153083324432373},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.612730860710144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6101479530334473},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5392924547195435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4480642080307007},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08496221899986267}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.89061039686203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153083324432373},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.612730860710144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6101479530334473},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5392924547195435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4480642080307007},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08496221899986267},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2018.2790981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2790981","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:29771673","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29771673","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":"Journal Article"},{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_51033","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_51033","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/d7f89b73-44c6-4f9d-ace9-c5e68c1c2c9f/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems, 29, 6, 2216-2226","raw_type":"http://purl.org/coar/resource_type/c_6501"}],"best_oa_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_51033","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_51033","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/d7f89b73-44c6-4f9d-ace9-c5e68c1c2c9f/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems, 29, 6, 2216-2226","raw_type":"http://purl.org/coar/resource_type/c_6501"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2172947564","display_name":"\u5927\u6570\u636e\u80cc\u666f\u4e0b\u7684\u9879\u76ee\u7ba1\u7406\u7406\u8bba\u4e0e\u6a21\u5f0f\u7814\u7a76","funder_award_id":"71732003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G279777322","display_name":"Enhancing control capabilities and robustness in the engineering of quantum ensembles","funder_award_id":"DP130101658","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G4793815275","display_name":null,"funder_award_id":"71732003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5078422264","display_name":null,"funder_award_id":"2016YFD0702100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5394304682","display_name":"\u9762\u5411\u5927\u6570\u636e\u7684\u77e5\u8bc6\u8868\u793a\u3001\u63a8\u7406\u3001\u5728\u7ebf\u5b66\u4e60\u7406\u8bba\u53ca\u5e94\u7528\u7814\u7a76","funder_award_id":"61432008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6947839359","display_name":"\u76f4\u89c9\u6a21\u7cca\u4fe1\u606f\u4e0b\u7684\u4e09\u652f\u51b3\u7b56\u7c97\u7cd9\u96c6\u65b9\u6cd5\u53ca\u77e5\u8bc6\u83b7\u53d6\u7814\u7a76","funder_award_id":"71671086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8611896717","display_name":null,"funder_award_id":"2016YFD0702100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2793798239.pdf","grobid_xml":"https://content.openalex.org/works/W2793798239.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W880548201","https://openalex.org/W1589747210","https://openalex.org/W1646707810","https://openalex.org/W1968962398","https://openalex.org/W1996625075","https://openalex.org/W2002196558","https://openalex.org/W2005874308","https://openalex.org/W2022508996","https://openalex.org/W2048687352","https://openalex.org/W2052688942","https://openalex.org/W2063756240","https://openalex.org/W2100913937","https://openalex.org/W2119333483","https://openalex.org/W2130942839","https://openalex.org/W2131494463","https://openalex.org/W2132984949","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2154997814","https://openalex.org/W2155968351","https://openalex.org/W2159420891","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2172612767","https://openalex.org/W2201581102","https://openalex.org/W2256388387","https://openalex.org/W2288565641","https://openalex.org/W2296073425","https://openalex.org/W2327501763","https://openalex.org/W2342792901","https://openalex.org/W2345837149","https://openalex.org/W2746553466","https://openalex.org/W2951799221","https://openalex.org/W2962826786","https://openalex.org/W2963260202","https://openalex.org/W2963333747","https://openalex.org/W2963390466","https://openalex.org/W2963699608","https://openalex.org/W2963864421","https://openalex.org/W3148685027","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W4298445375","https://openalex.org/W4298857966","https://openalex.org/W6623904765","https://openalex.org/W6675038308","https://openalex.org/W6679390333","https://openalex.org/W6679436768","https://openalex.org/W6683452725","https://openalex.org/W6684191040","https://openalex.org/W6685444567","https://openalex.org/W6691895530"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3],"new":[4],"training":[5,141,174],"paradigm":[6,142],"is":[7,88,111,145],"proposed":[8,22,139],"for":[9,82,92,150,178],"deep":[10,23,98,153,179],"reinforcement":[11,25,154,180],"learning":[12,17,26,155],"using":[13],"self-paced":[14,58,66],"prioritized":[15,103],"curriculum":[16,24,81,140],"with":[18],"coverage":[19,63,86],"penalty.":[20,64],"The":[21,50,65,85],"(DCRL)":[27],"takes":[28],"the":[29,45,69,72,76,79,108,118,138,165],"most":[30,129],"advantage":[31],"of":[32,47,52,57,78,130,143],"experience":[33,104],"replay":[34,41,105],"by":[35],"adaptively":[36],"selecting":[37],"appropriate":[38],"transitions":[39],"from":[40],"memory":[42],"based":[43],"on":[44,113,128],"complexity":[46,53],"each":[48],"transition.":[49],"criteria":[51],"in":[54],"DCRL":[55,109,123,144,170],"consist":[56],"priority":[59,67],"as":[60,62,158],"well":[61],"reflects":[68],"relationship":[70],"between":[71],"temporal-difference":[73],"error":[74],"and":[75,102,117,126,148,161,176],"difficulty":[77],"current":[80],"sample":[83,93],"efficiency.":[84],"penalty":[87],"taken":[89],"into":[90],"account":[91],"diversity.":[94],"With":[95],"comparison":[96],"to":[97],"Q":[99],"network":[100],"(DQN)":[101],"(PER)":[106],"methods,":[107],"algorithm":[110],"evaluated":[112],"Atari":[114],"2600":[115],"games,":[116],"experimental":[119,166],"results":[120,134,167],"show":[121,136],"that":[122,137,169],"outperforms":[124],"DQN":[125,160],"PER":[127],"these":[131],"games.":[132],"More":[133],"further":[135],"also":[146],"applicable":[147],"effective":[149],"other":[151],"memory-based":[152],"approaches,":[156],"such":[157],"double":[159],"dueling":[162],"network.":[163],"All":[164],"demonstrate":[168],"can":[171],"achieve":[172],"improved":[173],"efficiency":[175],"robustness":[177],"learning.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":5}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}