{"id":"https://openalex.org/W4411385785","doi":"https://doi.org/10.1080/00207721.2025.2515227","title":"Inverse reinforcement learning for discrete-time nonlinear systems: applications in circuits and systems","display_name":"Inverse reinforcement learning for discrete-time nonlinear systems: applications in circuits and systems","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411385785","doi":"https://doi.org/10.1080/00207721.2025.2515227"},"language":"en","primary_location":{"id":"doi:10.1080/00207721.2025.2515227","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2025.2515227","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","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/A5033337924","display_name":"Pengxu Ren","orcid":"https://orcid.org/0000-0002-5548-6365"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxu Ren","raw_affiliation_strings":["China University of Mining and Technology"],"raw_orcid":"https://orcid.org/0000-0002-5548-6365","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085295698","display_name":"Wei Dai","orcid":"https://orcid.org/0000-0003-3057-7225"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Dai","raw_affiliation_strings":["China University of Mining and Technology"],"raw_orcid":"https://orcid.org/0000-0003-3057-7225","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069826865","display_name":"Lei Ma","orcid":"https://orcid.org/0000-0001-8669-5613"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ma","raw_affiliation_strings":["China University of Mining and Technology"],"raw_orcid":"https://orcid.org/0000-0001-8669-5613","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055615832","display_name":"Chunyu Yang","orcid":"https://orcid.org/0000-0002-1590-1712"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Yang","raw_affiliation_strings":["China University of Mining and Technology"],"raw_orcid":"https://orcid.org/0000-0002-1590-1712","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085295698"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14449261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"57","issue":"3","first_page":"883","last_page":"893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9775999784469604,"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/nonlinear-system","display_name":"Nonlinear system","score":0.6614694595336914},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.6093012094497681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.526123046875},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5224032402038574},{"id":"https://openalex.org/keywords/electronic-circuit","display_name":"Electronic circuit","score":0.5149996280670166},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5106804966926575},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41800954937934875},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.36900657415390015},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33780637383461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2988321781158447},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.25500380992889404},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13413551449775696},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.10247370600700378},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10179951786994934}],"concepts":[{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6614694595336914},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.6093012094497681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.526123046875},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5224032402038574},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.5149996280670166},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5106804966926575},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41800954937934875},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.36900657415390015},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33780637383461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2988321781158447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25500380992889404},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13413551449775696},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.10247370600700378},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10179951786994934},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/00207721.2025.2515227","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2025.2515227","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1361279277","display_name":null,"funder_award_id":"BK20240102","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G214723977","display_name":null,"funder_award_id":"62373361","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1603698551","https://openalex.org/W1969959431","https://openalex.org/W1999874108","https://openalex.org/W2081514674","https://openalex.org/W2093831009","https://openalex.org/W2132858840","https://openalex.org/W2394967553","https://openalex.org/W2421813542","https://openalex.org/W2484646121","https://openalex.org/W2767307332","https://openalex.org/W2883304004","https://openalex.org/W3025041488","https://openalex.org/W3094638344","https://openalex.org/W3186624155","https://openalex.org/W3195939281","https://openalex.org/W3213059358","https://openalex.org/W4205353506","https://openalex.org/W4205496101","https://openalex.org/W4234864142","https://openalex.org/W4280599139","https://openalex.org/W4290991295","https://openalex.org/W4318604516","https://openalex.org/W4366608991","https://openalex.org/W4386390175","https://openalex.org/W4387886070","https://openalex.org/W4389232974","https://openalex.org/W4394698968","https://openalex.org/W4400188293","https://openalex.org/W4405535298","https://openalex.org/W4408323902"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"a":[3,45,75,84,124],"novel":[4],"inverse":[5,13,49,96],"reinforcement":[6],"learning":[7,78,87],"(RL)":[8],"algorithm":[9,51,73,98],"to":[10,38,57,102,133],"address":[11],"the":[12,36,40,55,59,64,70,104,109,114,135,138],"optimal":[14,91],"control":[15,85,140],"(IOC)":[16],"problem":[17],"in":[18],"discrete-time":[19],"nonlinear":[20],"circuits":[21],"and":[22,34,83,116,123],"systems":[23],"with":[24],"unknown":[25,60],"performance":[26,61,76],"function.":[27],"We":[28],"consider":[29],"an":[30,94,131],"expert-learner":[31],"imitation":[32],"structure,":[33],"adopt":[35],"learner":[37,56,115],"mimic":[39],"expert\u2019s":[41],"behaviour":[42,67],"trajectories.":[43],"Initially,":[44],"model-based":[46],"value":[47],"iteration":[48],"RL":[50,97],"is":[52,99,121,128],"developed,":[53],"enabling":[54],"reconstruct":[58],"function":[62,77],"utilising":[63],"observed":[65],"demonstration":[66],"trajectories":[68],"from":[69,81,90],"expert.":[71,117],"The":[72],"includes":[74],"stage":[79,88],"derived":[80,89],"IOC":[82],"policy":[86],"control.":[92],"Subsequently,":[93],"actor-critic-based":[95],"further":[100],"implemented":[101],"obviate":[103],"need":[105],"for":[106,112],"information":[107],"about":[108],"system":[110],"dynamics":[111],"both":[113],"Finally,":[118],"theoretical":[119],"analysis":[120],"provided,":[122],"boost":[125],"converter":[126],"circuit":[127],"used":[129],"as":[130],"example":[132],"demonstrate":[134],"effectiveness":[136],"of":[137],"proposed":[139],"algorithms.":[141]},"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}