{"id":"https://openalex.org/W2909020706","doi":"https://doi.org/10.1109/cbs.2018.8612197","title":"Continuous Reinforcement Learning With Knowledge-Inspired Reward Shaping for Autonomous Cavity Filter Tuning","display_name":"Continuous Reinforcement Learning With Knowledge-Inspired Reward Shaping for Autonomous Cavity Filter Tuning","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2909020706","doi":"https://doi.org/10.1109/cbs.2018.8612197","mag":"2909020706"},"language":"en","primary_location":{"id":"doi:10.1109/cbs.2018.8612197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbs.2018.8612197","pdf_url":null,"source":{"id":"https://openalex.org/S4306498323","display_name":"2018 IEEE International Conference on Cyborg and Bionic Systems (CBS)","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":"2018 IEEE International Conference on Cyborg and Bionic Systems (CBS)","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/A5089568886","display_name":"Zhiyang Wang","orcid":"https://orcid.org/0000-0003-2836-4060"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyang Wang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066181483","display_name":"Yongsheng Ou","orcid":"https://orcid.org/0000-0003-2998-267X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongsheng Ou","raw_affiliation_strings":["Yongsheng Ou and Xinyu Wu are with Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yongsheng Ou and Xinyu Wu are with Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352764","display_name":"Xinyu Wu","orcid":"https://orcid.org/0000-0001-6130-7821"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Wu","raw_affiliation_strings":["Yongsheng Ou and Xinyu Wu are with Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yongsheng Ou and Xinyu Wu are with Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052037779","display_name":"Wei Feng","orcid":"https://orcid.org/0000-0002-9845-999X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Feng","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"58"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9313704967498779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500259876251221},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7089000940322876},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6871160268783569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6121147274971008},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5728600025177002},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5691829919815063},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.482085257768631},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3589995503425598},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.213380366563797},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14781558513641357},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09879037737846375},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08439365029335022}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9313704967498779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500259876251221},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7089000940322876},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6871160268783569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121147274971008},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5728600025177002},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5691829919815063},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.482085257768631},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3589995503425598},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.213380366563797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14781558513641357},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09879037737846375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08439365029335022},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbs.2018.8612197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbs.2018.8612197","pdf_url":null,"source":{"id":"https://openalex.org/S4306498323","display_name":"2018 IEEE International Conference on Cyborg and Bionic Systems (CBS)","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":"2018 IEEE International Conference on Cyborg and Bionic Systems (CBS)","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":19,"referenced_works":["https://openalex.org/W1864417553","https://openalex.org/W2098132049","https://openalex.org/W2106610635","https://openalex.org/W2109747629","https://openalex.org/W2118080882","https://openalex.org/W2136515137","https://openalex.org/W2145339207","https://openalex.org/W2149984847","https://openalex.org/W2163565462","https://openalex.org/W2173248099","https://openalex.org/W2289573517","https://openalex.org/W2397581010","https://openalex.org/W2524982318","https://openalex.org/W2963864421","https://openalex.org/W3037791049","https://openalex.org/W3215083394","https://openalex.org/W6674950972","https://openalex.org/W6684921986","https://openalex.org/W6712392314"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W4306904969","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W2094012830","https://openalex.org/W187246281"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"has":[2],"achieved":[3],"a":[4,38,58,79,124],"great":[5],"success":[6],"in":[7,62,101],"recent":[8],"decades":[9],"when":[10],"applying":[11],"to":[12,37,109,121,127],"the":[13,35,52,102,111,129],"fields":[14],"such":[15],"as":[16],"finance,":[17],"robotics,":[18],"and":[19,31,92],"multi-agent":[20],"games.":[21],"A":[22],"variety":[23],"of":[24,113],"traditional":[25],"manual":[26,60],"tasks":[27],"are":[28,107],"facing":[29],"upgrading,":[30],"reinforcement":[32],"learning":[33],"opens":[34],"door":[36],"whole":[39],"new":[40],"world":[41],"for":[42,87],"improving":[43],"these":[44],"tasks.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"focus":[50],"on":[51,74,82],"task":[53],"called":[54],"Cavity":[55],"Filter":[56],"Tuning,":[57],"traditionally":[59],"work":[61],"communication":[63],"industries":[64],"which":[65],"not":[66],"only":[67],"consumes":[68],"time,":[69],"but":[70],"also":[71],"highly":[72],"depends":[73],"human":[75,99],"knowledge.":[76],"We":[77],"present":[78],"framework":[80],"based":[81],"Deep":[83],"Deterministic":[84],"Policy":[85],"Gradient":[86],"automatically":[88],"tuning":[89,103],"cavity":[90],"filters,":[91],"design":[93,130],"appropriate":[94],"reward":[95],"functions":[96],"inspired":[97],"by":[98],"expertise":[100],"task.":[104],"Simulation":[105],"experiments":[106],"conducted":[108],"validate":[110],"applicability":[112],"our":[114],"algorithm.":[115],"Our":[116],"proposed":[117],"method":[118],"is":[119],"able":[120],"autonomously":[122],"tune":[123],"detuned":[125],"filter":[126],"meet":[128],"specifications":[131],"from":[132],"any":[133],"random":[134],"starting":[135],"positions.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}