{"id":"https://openalex.org/W3094023755","doi":"https://doi.org/10.1109/cacre50138.2020.9230273","title":"Learning to Modulate Action of Deterministic Policy for Autonomous Navigation","display_name":"Learning to Modulate Action of Deterministic Policy for Autonomous Navigation","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W3094023755","doi":"https://doi.org/10.1109/cacre50138.2020.9230273","mag":"3094023755"},"language":"en","primary_location":{"id":"doi:10.1109/cacre50138.2020.9230273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cacre50138.2020.9230273","pdf_url":null,"source":{"id":"https://openalex.org/S4306498616","display_name":"2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100363116","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0003-1950-2468"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["State Laboratory of Industrial Control Technology, College of Control Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Laboratory of Industrial Control Technology, College of Control Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838","https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100962035","display_name":"Ke Zhu","orcid":"https://orcid.org/0009-0007-6338-4151"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhu","raw_affiliation_strings":["Institute of Robotics, Zhejiang University, Yuyao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Robotics, Zhejiang University, Yuyao, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427565","display_name":"Jianming Zhang","orcid":"https://orcid.org/0000-0002-4278-0805"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianming Zhang","raw_affiliation_strings":["State Laboratory of Industrial Control Technology, College of Control Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Laboratory of Industrial Control Technology, College of Control Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838","https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12253387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"697","last_page":"701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9987999796867371,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7419707775115967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7418853640556335},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.7365621328353882},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6076231598854065},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.596623420715332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354834794998169},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5053160786628723},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5045574903488159},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4197341203689575},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.342669278383255},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08886858820915222}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7419707775115967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418853640556335},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.7365621328353882},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6076231598854065},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.596623420715332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354834794998169},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5053160786628723},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5045574903488159},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4197341203689575},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.342669278383255},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08886858820915222},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cacre50138.2020.9230273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cacre50138.2020.9230273","pdf_url":null,"source":{"id":"https://openalex.org/S4306498616","display_name":"2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1522301498","https://openalex.org/W1777239053","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2146881125","https://openalex.org/W2153353727","https://openalex.org/W2163812848","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2542735967","https://openalex.org/W2567015638","https://openalex.org/W2904675649","https://openalex.org/W2962887844","https://openalex.org/W2963780790","https://openalex.org/W2963864421","https://openalex.org/W2963946945","https://openalex.org/W2964121744","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3104753760","https://openalex.org/W4297795161","https://openalex.org/W4302570325","https://openalex.org/W6631190155","https://openalex.org/W6638088447","https://openalex.org/W6682227427","https://openalex.org/W6684921986","https://openalex.org/W6731334075","https://openalex.org/W6750106230","https://openalex.org/W6772005887"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Unmanned":[0],"mobile":[1,26,35],"robots":[2,27,36],"are":[3],"widely":[4],"used":[5],"in":[6,39,53,67,84],"un-known":[7],"environments,":[8],"where":[9],"the":[10,88,95,102],"exact":[11],"overall":[12],"arrangement":[13],"of":[14,80,87],"environments":[15,69],"may":[16,59],"not":[17,60],"be":[18,51,61],"available.":[19],"This":[20],"paper":[21],"investigates":[22],"navigation":[23,65,108],"strategy":[24],"for":[25,94],"based":[28],"on":[29],"reinforcement":[30],"learning":[31,77],"method":[32],"to":[33,37,50,63,71],"allow":[34],"navigate":[38],"such":[40],"environments.":[41],"Deterministic":[42],"policy":[43,58,82],"gradient":[44],"algorithm":[45],"has":[46],"recently":[47],"been":[48],"shown":[49],"effective":[52],"complex":[54],"tasks.":[55],"However,":[56],"deterministic":[57],"safe":[62],"solve":[64],"problem":[66],"unknown":[68],"due":[70],"its":[72],"determinacy.":[73],"We":[74],"propose":[75],"a":[76,92],"framework":[78,104],"composed":[79],"dual":[81],"networks,":[83],"which":[85],"one":[86],"policies":[89],"acts":[90],"as":[91],"tuner":[93],"other.":[96],"Multiple":[97],"simulation":[98],"results":[99],"demonstrate":[100],"that":[101],"proposed":[103],"implicitly":[105],"learns":[106],"key":[107],"ability":[109],"and":[110],"is":[111],"more":[112],"efficient":[113],"than":[114],"baseline":[115],"method.":[116]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
