{"id":"https://openalex.org/W2570734388","doi":"https://doi.org/10.1109/cdc.2016.7798980","title":"Learning state representation for deep actor-critic control","display_name":"Learning state representation for deep actor-critic control","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2570734388","doi":"https://doi.org/10.1109/cdc.2016.7798980","mag":"2570734388"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7798980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","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/A5052292140","display_name":"Jelle Munk","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":"Jelle Munk","raw_affiliation_strings":["Delft Center for Systems and Control of Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control of Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"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":"Jens Kober","raw_affiliation_strings":["Delft Center for Systems and Control of Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control of Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","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 of Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control of Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4667","last_page":"4673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9955000281333923,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9679999947547913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6532811522483826},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6238080263137817},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.6105196475982666},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.542602002620697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4935420751571655},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41468656063079834},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15593299269676208},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09461554884910583},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07071501016616821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532811522483826},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6238080263137817},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.6105196475982666},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.542602002620697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4935420751571655},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41468656063079834},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15593299269676208},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09461554884910583},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07071501016616821},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2016.7798980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:1830de68-f008-471f-898f-0665c2a907d2","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:1830de68-f008-471f-898f-0665c2a907d2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1522301498","https://openalex.org/W1626155273","https://openalex.org/W1966086707","https://openalex.org/W1968962398","https://openalex.org/W1970890515","https://openalex.org/W2017957151","https://openalex.org/W2029514605","https://openalex.org/W2089434629","https://openalex.org/W2091565802","https://openalex.org/W2094024286","https://openalex.org/W2133233905","https://openalex.org/W2137376508","https://openalex.org/W2145339207","https://openalex.org/W2146444479","https://openalex.org/W2155027007","https://openalex.org/W2159008857","https://openalex.org/W2163922914","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2266673418","https://openalex.org/W2296691800","https://openalex.org/W2443711627","https://openalex.org/W2963864421","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W3148685027","https://openalex.org/W4302570325","https://openalex.org/W6606719070","https://openalex.org/W6631190155","https://openalex.org/W6679847170","https://openalex.org/W6683204974","https://openalex.org/W6683354640","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6693343427"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W2939353110","https://openalex.org/W2126887587","https://openalex.org/W4230611425","https://openalex.org/W2948658236","https://openalex.org/W2941846814","https://openalex.org/W3118091236","https://openalex.org/W3164822677"],"abstract_inverted_index":{"Deep":[0,79],"Neural":[1],"Networks":[2],"(DNNs)":[3],"can":[4,21,39,145],"be":[5],"used":[6,127],"as":[7],"function":[8],"approximators":[9],"in":[10,160,170],"Reinforcement":[11],"Learning":[12,78],"(RL).":[13],"One":[14],"advantage":[15],"of":[16,28,48,60,133],"DNNs":[17,38],"is":[18,52,67,84,125],"that":[19,53,86,142,154],"they":[20],"cope":[22],"with":[23,89],"large":[24,58],"input":[25,36,99],"dimensions.":[26],"Instead":[27],"relying":[29],"on":[30],"feature":[31],"engineering":[32],"to":[33,101,119,128,172],"lower":[34],"the":[35,41,106,130,134,143,167],"dimension,":[37],"extract":[40],"features":[42],"from":[43,97,151],"raw":[44],"observations.":[45],"The":[46,109],"drawback":[47],"this":[49,72,163],"end-to-end":[50,173],"learning":[51,94],"it":[54],"usually":[55],"requires":[56],"a":[57,74,95,102,113,121],"amount":[59],"data,":[61],"which":[62,124],"for":[63],"real-world":[64],"control":[65,149],"applications":[66],"not":[68],"always":[69],"available.":[70],"In":[71],"paper,":[73],"new":[75],"algorithm,":[76],"Model":[77],"Deterministic":[80],"Policy":[81],"Gradient":[82],"(ML-DDPG),":[83],"proposed":[85],"combines":[87],"RL":[88,107],"state":[90,103],"representation":[91],"learning,":[92],"i.e.,":[93],"mapping":[96],"an":[98],"vector":[100],"before":[104],"solving":[105],"task.":[108],"ML-DDPG":[110,144],"algorithm":[111],"uses":[112],"concept":[114],"we":[115],"call":[116],"predictive":[117],"priors":[118],"learn":[120,146],"model":[122],"network":[123],"subsequently":[126],"pre-train":[129],"first":[131],"layer":[132],"actor":[135],"and":[136],"critic":[137],"networks.":[138],"Simulation":[139],"results":[140],"show":[141],"reasonable":[147],"continuous":[148],"policies":[150],"high-dimensional":[152],"observations":[153],"contain":[155],"also":[156],"task-irrelevant":[157],"information.":[158],"Furthermore,":[159],"some":[161],"cases,":[162],"approach":[164],"significantly":[165],"improves":[166],"final":[168],"performance":[169],"comparison":[171],"learning.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}