{"id":"https://openalex.org/W2120528496","doi":"https://doi.org/10.1109/tcyb.2014.2343194","title":"Reinforcement Learning for Port-Hamiltonian Systems","display_name":"Reinforcement Learning for Port-Hamiltonian Systems","publication_year":2014,"publication_date":"2014-08-26","ids":{"openalex":"https://openalex.org/W2120528496","doi":"https://doi.org/10.1109/tcyb.2014.2343194","mag":"2120528496","pmid":"https://pubmed.ncbi.nlm.nih.gov/25167564"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2014.2343194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2014.2343194","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1212.5524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076416455","display_name":"Olivier Sprangers","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Olivier Sprangers","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061604841","display_name":"Subramanya Nageshrao","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Subramanya P. Nageshrao","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046652464","display_name":"Gabriel A. D. Lopes","orcid":"https://orcid.org/0000-0002-2406-9489"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gabriel A. D. Lopes","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076416455"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":3.6923,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.9340989,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"45","issue":"5","first_page":"1017","last_page":"1027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12772","display_name":"Control and Stability of Dynamical Systems","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12772","display_name":"Control and Stability of Dynamical Systems","score":0.9997000098228455,"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/T12763","display_name":"ATP Synthase and ATPases Research","score":0.967199981212616,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.945900022983551,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7853497266769409},{"id":"https://openalex.org/keywords/passivity","display_name":"Passivity","score":0.7615072727203369},{"id":"https://openalex.org/keywords/hamiltonian","display_name":"Hamiltonian (control theory)","score":0.5960972905158997},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5922336578369141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5914492607116699},{"id":"https://openalex.org/keywords/hamiltonian-system","display_name":"Hamiltonian system","score":0.4403374195098877},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4210437834262848},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.34982556104660034},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.28020840883255005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2414579689502716},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.22410833835601807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20445680618286133},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18423298001289368}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7853497266769409},{"id":"https://openalex.org/C2778809601","wikidata":"https://www.wikidata.org/wiki/Q1045736","display_name":"Passivity","level":2,"score":0.7615072727203369},{"id":"https://openalex.org/C130787639","wikidata":"https://www.wikidata.org/wiki/Q5645293","display_name":"Hamiltonian (control theory)","level":2,"score":0.5960972905158997},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5922336578369141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914492607116699},{"id":"https://openalex.org/C121770821","wikidata":"https://www.wikidata.org/wiki/Q2072471","display_name":"Hamiltonian system","level":2,"score":0.4403374195098877},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4210437834262848},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.34982556104660034},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28020840883255005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2414579689502716},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.22410833835601807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20445680618286133},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18423298001289368},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcyb.2014.2343194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2014.2343194","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:25167564","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25167564","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 cybernetics","raw_type":null},{"id":"pmh:oai:arXiv.org:1212.5524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1212.5524","pdf_url":"https://arxiv.org/pdf/1212.5524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1212.5524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1212.5524","pdf_url":"https://arxiv.org/pdf/1212.5524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W118959678","https://openalex.org/W127505597","https://openalex.org/W1495978235","https://openalex.org/W1541507932","https://openalex.org/W1553823556","https://openalex.org/W1966086707","https://openalex.org/W1966124127","https://openalex.org/W1979638690","https://openalex.org/W2009303086","https://openalex.org/W2014441923","https://openalex.org/W2020940402","https://openalex.org/W2028593157","https://openalex.org/W2046376809","https://openalex.org/W2091565802","https://openalex.org/W2106261932","https://openalex.org/W2108810732","https://openalex.org/W2114910670","https://openalex.org/W2117941826","https://openalex.org/W2121863487","https://openalex.org/W2122739526","https://openalex.org/W2125710232","https://openalex.org/W2132875296","https://openalex.org/W2139361041","https://openalex.org/W2144355672","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2159791355","https://openalex.org/W2169476413","https://openalex.org/W2305677499","https://openalex.org/W2736458191","https://openalex.org/W2962860455","https://openalex.org/W4214690803","https://openalex.org/W4214717370","https://openalex.org/W6629542745","https://openalex.org/W6633001767","https://openalex.org/W6676072908","https://openalex.org/W6678635437","https://openalex.org/W6683204974","https://openalex.org/W6698100548"],"related_works":["https://openalex.org/W4233304828","https://openalex.org/W4239268637","https://openalex.org/W2952841825","https://openalex.org/W1977819874","https://openalex.org/W2051296765","https://openalex.org/W2960878236","https://openalex.org/W153449849","https://openalex.org/W2473698078","https://openalex.org/W2085176909","https://openalex.org/W2010551470"],"abstract_inverted_index":{"Passivity-based":[0],"control":[1,30,69,128,142],"(PBC)":[2],"for":[3,140,186],"port-Hamiltonian":[4,190],"systems":[5,191],"provides":[6],"an":[7],"intuitive":[8],"way":[9],"of":[10,76,113,126,162,189,208],"achieving":[11],"stabilization":[12],"by":[13,44,132],"rendering":[14],"a":[15,21,46,60,74,96,114,145],"system":[16],"passive":[17],"with":[18],"respect":[19],"to":[20,41,54,85,98,172,192,204,217],"desired":[22,116,146],"storage":[23],"function.":[24],"However,":[25],"in":[26,78,160,195,222],"most":[27],"instances":[28],"the":[29,66,80,86,89,103,111,127,138,154,180,187,196,201,205,209,218],"law":[31,129],"is":[32,73,83,122,152],"obtained":[33],"without":[34],"any":[35],"performance":[36,119],"considerations":[37],"and":[38,91,121,165,224],"it":[39,170],"has":[40,213],"be":[42,158,193],"calculated":[43],"solving":[45],"complex":[47],"partial":[48],"differential":[49],"equation":[50],"(PDE).":[51],"In":[52],"order":[53],"address":[55],"these":[56],"issues":[57],"we":[58],"introduce":[59],"reinforcement":[61],"learning":[62,202],"(RL)":[63],"approach":[64],"into":[65],"energy-balancing":[67],"passivity-based":[68],"(EB-PBC)":[70],"method,":[71],"which":[72,79,168],"form":[75],"PBC":[77],"closed-loop":[81,147],"energy":[82,148,163],"equal":[84],"difference":[87],"between":[88],"stored":[90],"supplied":[92],"energies.":[93],"We":[94],"propose":[95],"technique":[97],"parameterize":[99],"EB-PBC":[100],"that":[101,153],"preserves":[102],"systems's":[104],"PDE":[105],"matching":[106],"conditions,":[107],"does":[108],"not":[109],"require":[110],"specification":[112],"global":[115],"Hamiltonian,":[117],"includes":[118],"criteria,":[120],"robust.":[123],"The":[124,150,211],"parameters":[125],"are":[130],"found":[131],"using":[133,176],"actor-critic":[134],"(AC)":[135],"RL,":[136],"enabling":[137],"search":[139],"near-optimal":[141],"policies":[143],"satisfying":[144],"landscape.":[149],"advantage":[151],"solutions":[155],"learned":[156],"can":[157],"interpreted":[159],"terms":[161],"shaping":[164],"damping":[166],"injection,":[167],"makes":[169],"possible":[171],"numerically":[173],"assess":[174],"stability":[175],"passivity":[177],"theory.":[178],"From":[179],"RL":[181],"perspective,":[182],"our":[183],"proposal":[184],"allows":[185],"class":[188],"incorporated":[194],"AC":[197],"framework,":[198],"speeding":[199],"up":[200],"thanks":[203],"resulting":[206],"parameterization":[207],"policy.":[210],"method":[212],"been":[214],"successfully":[215],"applied":[216],"pendulum":[219],"swing-up":[220],"problem":[221],"simulations":[223],"real-life":[225],"experiments.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}