{"id":"https://openalex.org/W1986278286","doi":"https://doi.org/10.1109/iros.2010.5650345","title":"Control delay in Reinforcement Learning for real-time dynamic systems: A memoryless approach","display_name":"Control delay in Reinforcement Learning for real-time dynamic systems: A memoryless approach","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W1986278286","doi":"https://doi.org/10.1109/iros.2010.5650345","mag":"1986278286"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2010.5650345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5650345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5031675619","display_name":"E. Schuitema","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":"E Schuitema","raw_affiliation_strings":["Delft Biorobotics Laboratory, Delft University of Technnology, Delft, Netherlands","Delft Biorobotics Lab, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Biorobotics Laboratory, Delft University of Technnology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Biorobotics Lab, The Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"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":"L Busoniu","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands","Delft Center for Systems and Control, Delft University of Technology, Mekelweg 2, 2628CD, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Mekelweg 2, 2628CD, 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":"R Babuska","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands","Delft Center for Systems and Control, Delft University of Technology, Mekelweg 2, 2628CD, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Mekelweg 2, 2628CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009602174","display_name":"Pieter Jonker","orcid":"https://orcid.org/0000-0002-5939-7415"},"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":"P Jonker","raw_affiliation_strings":["Delft Biorobotics Laboratory, Delft University of Technnology, Delft, Netherlands","Delft Biorobotics Lab, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Biorobotics Laboratory, Delft University of Technnology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Biorobotics Lab, The Netherlands","institution_ids":[]}]}],"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":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3226","last_page":"3231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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":0.9959999918937683,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9652000069618225,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10839","display_name":"Pancreatic function and diabetes","score":0.9502000212669373,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8555318713188171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6952843070030212},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6279362440109253},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5165818929672241},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.4539662301540375},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.44664227962493896},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4224380850791931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37063688039779663},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.34276896715164185},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10977798700332642}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8555318713188171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952843070030212},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6279362440109253},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5165818929672241},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.4539662301540375},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.44664227962493896},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4224380850791931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37063688039779663},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.34276896715164185},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10977798700332642},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":1,"locations":[{"id":"doi:10.1109/iros.2010.5650345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5650345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W1541084404","https://openalex.org/W1984120922","https://openalex.org/W2117864026","https://openalex.org/W2121863487","https://openalex.org/W2150339816","https://openalex.org/W2152520382","https://openalex.org/W2159566498","https://openalex.org/W4214717370","https://openalex.org/W6600231840"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W2152445738","https://openalex.org/W3038962357"],"abstract_inverted_index":{"Robots":[0],"controlled":[1],"by":[2,71],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"are":[6],"still":[7],"rare.":[8],"A":[9],"core":[10],"challenge":[11],"to":[12,17,21],"the":[13,24,30,73,86,93,100,107],"application":[14],"of":[15,26,92,102],"RL":[16],"robotic":[18,104],"systems":[19],"is":[20,43,88],"learn":[22],"despite":[23],"existence":[25],"control":[27,64,74],"delay":[28,31,42,75,87,108],"-":[29],"between":[32],"measuring":[33],"a":[34,83,103],"system's":[35],"state":[36],"and":[37],"acting":[38],"upon":[39],"it.":[40],"Control":[41],"always":[44],"present":[45,53],"in":[46,82,99],"real":[47],"systems.":[48],"In":[49,113],"this":[50],"work,":[51],"we":[52],"two":[54],"novel":[55],"temporal":[56],"difference":[57],"(TD)":[58],"learning":[59,69,122],"algorithms":[60,67,81,118],"for":[61],"problems":[62],"with":[63],"delay.":[65],"These":[66],"improve":[68],"performance":[70],"taking":[72],"into":[76],"account.":[77],"We":[78],"test":[79],"our":[80,116],"gridworld,":[84],"where":[85,106],"an":[89],"integer":[90],"multiple":[91],"time":[94],"step,":[95],"as":[96,98],"well":[97],"simulation":[101],"system,":[105],"can":[109],"have":[110],"any":[111],"value.":[112],"both":[114],"tests,":[115],"proposed":[117],"outperform":[119],"classical":[120],"TD":[121],"algorithms,":[123],"while":[124],"maintaining":[125],"low":[126],"computational":[127],"complexity.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}