{"id":"https://openalex.org/W3107113899","doi":"https://doi.org/10.1109/tcds.2020.3039859","title":"Tutor-Guided Interior Navigation With Deep Reinforcement Learning","display_name":"Tutor-Guided Interior Navigation With Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-11-25","ids":{"openalex":"https://openalex.org/W3107113899","doi":"https://doi.org/10.1109/tcds.2020.3039859","mag":"3107113899"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2020.3039859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.3039859","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5086740899","display_name":"Fanyu Zeng","orcid":"https://orcid.org/0000-0002-4883-5096"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fanyu Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Center for Robotics, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Robotics, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049697307","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-0236-269X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Center for Robotics, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Center for Robotics, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008501506","display_name":"Shuzhi Sam Ge","orcid":"https://orcid.org/0000-0001-5549-312X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Shuzhi Sam Ge","raw_affiliation_strings":["Department of Electrical Computer Engineering, National University of Singapore, Singapore","School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086740899"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.8231,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79750511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"13","issue":"4","first_page":"934","last_page":"944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tutor","display_name":"TUTOR","score":0.9608621597290039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8388359546661377},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7697837352752686},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5555753111839294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5025482177734375},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45515888929367065},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.41158610582351685},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08846503496170044},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06258967518806458}],"concepts":[{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.9608621597290039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388359546661377},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7697837352752686},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5555753111839294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5025482177734375},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45515888929367065},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.41158610582351685},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08846503496170044},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06258967518806458}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2020.3039859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.3039859","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4531927070","display_name":null,"funder_award_id":"U1813202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5767895881","display_name":null,"funder_award_id":"2018YFC0831800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6506257578","display_name":null,"funder_award_id":"62003381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7605923862","display_name":null,"funder_award_id":"61773093","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W169439271","https://openalex.org/W612478963","https://openalex.org/W1612997784","https://openalex.org/W1771410628","https://openalex.org/W1868739439","https://openalex.org/W1989484209","https://openalex.org/W2021712403","https://openalex.org/W2053123342","https://openalex.org/W2083421359","https://openalex.org/W2109994478","https://openalex.org/W2117228865","https://openalex.org/W2121477371","https://openalex.org/W2145339207","https://openalex.org/W2151290401","https://openalex.org/W2153054365","https://openalex.org/W2154280780","https://openalex.org/W2158334497","https://openalex.org/W2200124539","https://openalex.org/W2286538239","https://openalex.org/W2410639023","https://openalex.org/W2461937780","https://openalex.org/W2606794968","https://openalex.org/W2736601468","https://openalex.org/W2739423245","https://openalex.org/W2768829067","https://openalex.org/W2805984364","https://openalex.org/W2912259603","https://openalex.org/W2950872548","https://openalex.org/W2962887844","https://openalex.org/W2963019567","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2963871073","https://openalex.org/W2964043796","https://openalex.org/W2964935470","https://openalex.org/W2967853831","https://openalex.org/W2980730703","https://openalex.org/W3021208093","https://openalex.org/W3104933725","https://openalex.org/W3124420883","https://openalex.org/W4236769309","https://openalex.org/W4297795161","https://openalex.org/W4298857966","https://openalex.org/W6618872416","https://openalex.org/W6638018090","https://openalex.org/W6639180034","https://openalex.org/W6692405165","https://openalex.org/W6692846177","https://openalex.org/W6696350822","https://openalex.org/W6729556111","https://openalex.org/W6731334075","https://openalex.org/W6751885507"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W3111983280","https://openalex.org/W3164468573","https://openalex.org/W2329452785","https://openalex.org/W2356380379"],"abstract_inverted_index":{"Traditional":[0],"reinforcement":[1],"learning":[2,98],"makes":[3],"policy":[4],"based":[5],"on":[6],"the":[7,51,66,93,97,115,127],"current":[8],"system":[9,13],"state.":[10],"However,":[11],"insufficient":[12],"information":[14],"and":[15,110,124,133,147],"few":[16],"rewards":[17],"lead":[18],"to":[19,65,87,91,145],"its":[20],"limited":[21],"applicability,":[22],"especially":[23],"in":[24,105],"a":[25,37,54,61,88],"partially":[26],"observed":[27],"environment":[28,90],"with":[29,46,112,120],"sparse":[30],"rewards.":[31,137],"In":[32,50],"this":[33],"work,":[34],"we":[35],"propose":[36],"tutor\u2013student":[38,52],"network":[39,129],"(TSN)":[40],"for":[41],"improving":[42],"an":[43],"agent\u2019s":[44],"performance":[45,116],"additional":[47],"auxiliary":[48,58],"information.":[49],"framework,":[53],"tutor":[55,79],"module":[56,63,95],"generates":[57],"information,":[59],"while":[60],"student":[62,94],"refers":[64],"tutor\u2019s":[67],"suggestion":[68],"during":[69],"training.":[70],"The":[71],"key":[72],"of":[73,117],"our":[74,140],"proposed":[75,128],"approach":[76,141],"is":[77],"that":[78,83,126],"provides":[80],"prior":[81],"knowledge":[82],"does":[84],"not":[85],"correspond":[86],"specified":[89],"help":[92],"accelerate":[96],"procedure.":[99],"We":[100],"build":[101],"12":[102],"indoor":[103],"mazes":[104,109,111],"ViZDoom,":[106],"including":[107],"empty":[108],"obstacles,":[113],"evaluate":[114],"TSN":[118],"compared":[119],"advantage":[121],"actor\u2013critic":[122],"(A2C)":[123],"show":[125],"learned":[130],"navigation":[131],"faster":[132],"obtained":[134],"higher":[135],"accumulated":[136],"More":[138],"importantly,":[139],"could":[142],"generalize":[143],"well":[144],"new":[146],"unseen":[148],"domains.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}