{"id":"https://openalex.org/W4283699829","doi":"https://doi.org/10.1109/tnnls.2022.3184956","title":"Understanding via Exploration: Discovery of Interpretable Features With Deep Reinforcement Learning","display_name":"Understanding via Exploration: Discovery of Interpretable Features With Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W4283699829","doi":"https://doi.org/10.1109/tnnls.2022.3184956","pmid":"https://pubmed.ncbi.nlm.nih.gov/35763482"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3184956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3184956","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101432799","display_name":"Jiawen Wei","orcid":"https://orcid.org/0000-0001-5025-383X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Wei","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5025-383X","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025546736","display_name":"Zhifeng Qiu","orcid":"https://orcid.org/0000-0002-7076-4343"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Qiu","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7076-4343","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088586965","display_name":"Fangyuan Wang","orcid":"https://orcid.org/0000-0002-7492-632X"},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyuan Wang","raw_affiliation_strings":["School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7492-632X","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China","institution_ids":["https://openalex.org/I1328775524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100521766","display_name":"Wenwei Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwei Lin","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012277801","display_name":"Ning Gui","orcid":"https://orcid.org/0000-0003-4983-5327"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Gui","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4983-5327","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100711520","display_name":"Weihua Gui","orcid":"https://orcid.org/0000-0002-5337-6445"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua Gui","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-5337-6445","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0452,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79588027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"35","issue":"2","first_page":"1696","last_page":"1707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.993399977684021,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9930999875068665,"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":0.7002339959144592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.665799617767334},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6461957693099976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6399289965629578},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5191797018051147},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5134807229042053},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.45342493057250977},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45336347818374634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44865626096725464},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4480937123298645},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.442631334066391},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43332260847091675},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.360077828168869}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7002339959144592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665799617767334},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6461957693099976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6399289965629578},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5191797018051147},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5134807229042053},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.45342493057250977},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45336347818374634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44865626096725464},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4480937123298645},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.442631334066391},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43332260847091675},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.360077828168869},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3184956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3184956","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:35763482","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35763482","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":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3556697363","display_name":null,"funder_award_id":"62073345","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5623062188","display_name":null,"funder_award_id":"62011530148","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5789780205","display_name":null,"funder_award_id":"61988101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8219918639","display_name":"\u57fa\u4e8e\u573a\u666f\u753b\u50cf\u7684\u81ea\u9002\u5e94\u8f6f\u4ef6\u5728\u7ebf\u6f14\u5316\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772473","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1500895378","https://openalex.org/W1600437712","https://openalex.org/W1930624869","https://openalex.org/W2101234009","https://openalex.org/W2145339207","https://openalex.org/W2163922914","https://openalex.org/W2295598076","https://openalex.org/W2339611261","https://openalex.org/W2462006847","https://openalex.org/W2513205244","https://openalex.org/W2546571074","https://openalex.org/W2564216145","https://openalex.org/W2593309265","https://openalex.org/W2749807327","https://openalex.org/W2753415590","https://openalex.org/W2759903677","https://openalex.org/W2796096336","https://openalex.org/W2891830784","https://openalex.org/W2903659352","https://openalex.org/W2908300435","https://openalex.org/W2911681169","https://openalex.org/W2911964244","https://openalex.org/W2940009787","https://openalex.org/W2952203743","https://openalex.org/W2952561542","https://openalex.org/W2960532465","https://openalex.org/W2980039866","https://openalex.org/W3005778327","https://openalex.org/W3100661288","https://openalex.org/W3120689699","https://openalex.org/W3192022969","https://openalex.org/W4214717370","https://openalex.org/W4289236186","https://openalex.org/W6631190155","https://openalex.org/W6635902665","https://openalex.org/W6637461618","https://openalex.org/W6675354045","https://openalex.org/W6684921986","https://openalex.org/W6694177581","https://openalex.org/W6743756900","https://openalex.org/W6743846187","https://openalex.org/W6745609711","https://openalex.org/W6747585041","https://openalex.org/W6748336101","https://openalex.org/W6751794770","https://openalex.org/W6769099739","https://openalex.org/W6780559895","https://openalex.org/W6784145239"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W4360615883","https://openalex.org/W3034267371"],"abstract_inverted_index":{"Understanding":[0],"the":[1,9,40,62,75,86,89,92,98,108,126,130,134,147,152,156,188,196,211,219],"environments":[2],"through":[3,31],"interactions":[4],"has":[5,23,106],"been":[6,25],"one":[7,99],"of":[8,43,88,170],"most":[10,103],"important":[11],"human":[12,200],"intellectual":[13],"activities":[14],"in":[15,36,102,146,155,179],"mastering":[16],"unknown":[17],"systems.":[18,64],"Deep":[19],"reinforcement":[20],"learning":[21],"(DRL)":[22],"already":[24],"known":[26],"to":[27,55,84,133],"achieve":[28],"effective":[29],"control":[30,94,177],"human-like":[32],"exploration":[33],"and":[34,111,202],"exploitation":[35],"many":[37],"applications.":[38],"However,":[39],"opaque":[41],"nature":[42],"deep":[44],"neural":[45],"network":[46],"(DNN)":[47],"often":[48],"hides":[49],"critical":[50],"information":[51],"about":[52],"feature":[53,71,78,193,205,213],"relevance":[54],"control,":[56],"which":[57],"is":[58,81,172],"essential":[59],"for":[60],"understanding":[61],"target":[63],"In":[65,208],"this":[66],"article,":[67],"a":[68],"novel":[69],"online":[70],"selection":[72,79,206],"framework,":[73],"namely,":[74],"dual-world-based":[76],"attentive":[77],"(D-AFS),":[80],"first":[82],"proposed":[83],"identify":[85,162],"contribution":[87],"inputs":[90],"over":[91],"whole":[93],"process.":[95],"Rather":[96],"than":[97,195],"world":[100,110,132],"used":[101,221],"DRL,":[104],"D-AFS":[105,159,185],"both":[107],"real":[109,131],"its":[112],"virtual":[113,135],"peer":[114],"with":[115,141,218],"twisted":[116],"features.":[117],"The":[118,137],"newly":[119],"introduced":[120],"attention-based":[121],"evaluation":[122],"(AR)":[123],"module":[124],"performs":[125],"dynamic":[127,225],"mapping":[128],"from":[129],"world.":[136,149],"existing":[138],"DRL":[139],"algorithms,":[140],"slight":[142],"modification,":[143],"can":[144,160,186],"learn":[145],"dual":[148],"By":[150],"analyzing":[151],"DRL's":[153],"response":[154],"two":[157],"worlds,":[158],"quantitatively":[161],"respective":[163],"features'":[164],"importance":[165],"toward":[166],"control.":[167],"A":[168],"set":[169],"experiments":[171],"performed":[173],"on":[174],"four":[175],"classical":[176],"systems":[178],"OpenAI":[180],"Gym.":[181],"Results":[182],"show":[183],"that":[184],"generate":[187],"same":[189],"or":[190],"even":[191],"better":[192],"combinations":[194],"solutions":[197],"provided":[198],"by":[199,222],"experts":[201],"seven":[203],"recent":[204],"baselines.":[207],"all":[209],"cases,":[210],"selected":[212],"representations":[214],"are":[215],"closely":[216],"correlated":[217],"ones":[220],"underlying":[223],"system":[224],"models.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}