{"id":"https://openalex.org/W2102243232","doi":"https://doi.org/10.1109/irds.2002.1041532","title":"Approximating the value function for continuous space reinforcement learning in robot control","display_name":"Approximating the value function for continuous space reinforcement learning in robot control","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2102243232","doi":"https://doi.org/10.1109/irds.2002.1041532","mag":"2102243232"},"language":"en","primary_location":{"id":"doi:10.1109/irds.2002.1041532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","raw_type":"proceedings-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/A5083719559","display_name":"Sebastian Buck","orcid":"https://orcid.org/0000-0002-8925-5952"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"S. Buck","raw_affiliation_strings":["Munich University of Technology, Germany","Munich Univ. of Tech., Germany"],"affiliations":[{"raw_affiliation_string":"Munich University of Technology, Germany","institution_ids":["https://openalex.org/I174004417"]},{"raw_affiliation_string":"Munich Univ. of Tech., Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003274224","display_name":"Michael Beetz","orcid":"https://orcid.org/0000-0002-7888-7444"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Beetz","raw_affiliation_strings":["Munich University of Technology, Germany","Munich Univ. of Tech., Germany"],"affiliations":[{"raw_affiliation_string":"Munich University of Technology, Germany","institution_ids":["https://openalex.org/I174004417"]},{"raw_affiliation_string":"Munich Univ. of Tech., Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004595113","display_name":"Thorsten Schmitt","orcid":"https://orcid.org/0000-0002-5737-1094"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"T. Schmitt","raw_affiliation_strings":["Munich University of Technology, Germany","Munich Univ. of Tech., Germany"],"affiliations":[{"raw_affiliation_string":"Munich University of Technology, Germany","institution_ids":["https://openalex.org/I174004417"]},{"raw_affiliation_string":"Munich Univ. of Tech., Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083719559"],"corresponding_institution_ids":["https://openalex.org/I174004417","https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":1.8719,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87883478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"1062","last_page":"1067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.995199978351593,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8608381748199463},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6988688111305237},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6548906564712524},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6333936452865601},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6326904892921448},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6202973127365112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5604016184806824},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5379273295402527},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5007104873657227},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4976864159107208},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.49329203367233276},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.47330179810523987},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4489160180091858},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.438648521900177},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4374925494194031},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3590605854988098},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29134127497673035},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.19547316431999207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18903887271881104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13693666458129883}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8608381748199463},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6988688111305237},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6548906564712524},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6333936452865601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6326904892921448},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6202973127365112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5604016184806824},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5379273295402527},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5007104873657227},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4976864159107208},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.49329203367233276},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.47330179810523987},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4489160180091858},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.438648521900177},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4374925494194031},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3590605854988098},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29134127497673035},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.19547316431999207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18903887271881104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13693666458129883},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/irds.2002.1041532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/irds.2002.1041532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and System","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.2129","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.2129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www9.in.tum.de/publications/2002/IROS-2002-Buck-etal.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W92805021","https://openalex.org/W1495978126","https://openalex.org/W1517733364","https://openalex.org/W1576452626","https://openalex.org/W1583380718","https://openalex.org/W1585546346","https://openalex.org/W1601350066","https://openalex.org/W1857080389","https://openalex.org/W1966195676","https://openalex.org/W2053407718","https://openalex.org/W2113501460","https://openalex.org/W2125074935","https://openalex.org/W2142409110","https://openalex.org/W2143908786","https://openalex.org/W2152166054","https://openalex.org/W2155791599","https://openalex.org/W4214717370","https://openalex.org/W4231226883","https://openalex.org/W6602057636","https://openalex.org/W6603762378","https://openalex.org/W6683164292"],"related_works":["https://openalex.org/W1976452401","https://openalex.org/W4256087190","https://openalex.org/W1501190258","https://openalex.org/W2807018115","https://openalex.org/W4240668504","https://openalex.org/W2051622126","https://openalex.org/W2569146624","https://openalex.org/W2788366696","https://openalex.org/W2125074935","https://openalex.org/W2011233848"],"abstract_inverted_index":{"Many":[0],"robot":[1,80],"learning":[2,43],"tasks":[3],"are":[4,12,19,25],"very":[5],"difficult":[6],"to":[7,34,58,78,85],"solve:":[8],"their":[9],"state":[10],"spaces":[11],"high":[13],"dimensional,":[14],"variables":[15],"and":[16,22,64,93],"command":[17],"parameters":[18],"continuously":[20],"valued,":[21],"system":[23],"states":[24],"only":[26],"partly":[27],"observable.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"propose":[33],"learn":[35],"a":[36,60],"continuous":[37],"space":[38],"value":[39,72],"function":[40,55],"for":[41],"reinforcement":[42],"using":[44],"neural":[45],"networks":[46],"trained":[47],"from":[48],"data":[49],"of":[50],"exploration":[51],"runs.":[52],"The":[53],"learned":[54],"is":[56],"guaranteed":[57],"be":[59],"lower":[61],"bound":[62],"for,":[63],"reproduces":[65],"the":[66,70],"characteristic":[67],"shape":[68],"of,":[69],"accurate":[71],"function.":[73],"We":[74],"apply":[75],"our":[76],"approach":[77],"two":[79],"navigation":[81],"tasks,":[82],"discuss":[83],"how":[84],"deal":[86],"with":[87],"possible":[88],"problems":[89],"occurring":[90],"in":[91],"practice,":[92],"assess":[94],"its":[95],"performance.":[96]},"counts_by_year":[{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}