{"id":"https://openalex.org/W2024227045","doi":"https://doi.org/10.1109/adprl.2011.5967352","title":"Enhancing the episodic natural actor-critic algorithm by a regularisation term to stabilize learning of control structures","display_name":"Enhancing the episodic natural actor-critic algorithm by a regularisation term to stabilize learning of control structures","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2024227045","doi":"https://doi.org/10.1109/adprl.2011.5967352","mag":"2024227045"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5047626717","display_name":"Andreas Witsch","orcid":null},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Witsch","raw_affiliation_strings":["Distributed Systems Group, Universit\u00e4t Kassel, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Systems Group, Universit\u00e4t Kassel, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030390468","display_name":"Roland Reichle","orcid":null},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roland Reichle","raw_affiliation_strings":["Distributed Systems Group, Universit\u00e4t Kassel, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Systems Group, Universit\u00e4t Kassel, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077860593","display_name":"Kurt Geihs","orcid":"https://orcid.org/0000-0001-9833-6108"},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kurt Geihs","raw_affiliation_strings":["Distributed Systems Group, Universit\u00e4t Kassel, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Systems Group, Universit\u00e4t Kassel, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042382031","display_name":"Sascha Lange","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sascha Lange","raw_affiliation_strings":["Machine Learning Laboratory, Albert Ludwigs Universit\u00e4t Freiburg, Germany","Machine Learning Lab, Albert-Ludwigs-Universit\u00e4t Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Laboratory, Albert Ludwigs Universit\u00e4t Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Machine Learning Lab, Albert-Ludwigs-Universit\u00e4t Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Riedmiller","raw_affiliation_strings":["Machine Learning Laboratory, Albert Ludwigs Universit\u00e4t Freiburg, Germany","Machine Learning Lab, Albert-Ludwigs-Universit\u00e4t Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Laboratory, Albert Ludwigs Universit\u00e4t Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Machine Learning Lab, Albert-Ludwigs-Universit\u00e4t Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11523352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9728000164031982,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7732553482055664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6658254861831665},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6597334146499634},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.65474534034729},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6539071202278137},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5686216950416565},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.531130313873291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47683969140052795},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4748133420944214},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44780880212783813},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.417195200920105},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40314388275146484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.339663565158844},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33614397048950195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22720029950141907},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2254261076450348}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7732553482055664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658254861831665},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6597334146499634},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.65474534034729},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6539071202278137},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5686216950416565},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.531130313873291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47683969140052795},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4748133420944214},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44780880212783813},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.417195200920105},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40314388275146484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.339663565158844},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33614397048950195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22720029950141907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2254261076450348},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2011.5967352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.229.1029","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.1029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ml.informatik.uni-freiburg.de/_media/publications/wrlrg11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1555368087","https://openalex.org/W1663973292","https://openalex.org/W1670925118","https://openalex.org/W2101950184","https://openalex.org/W2119717200","https://openalex.org/W2125612430","https://openalex.org/W2146737184","https://openalex.org/W2150600804","https://openalex.org/W2155027007","https://openalex.org/W2172968643","https://openalex.org/W4214717370","https://openalex.org/W4300579247","https://openalex.org/W6637173446"],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W3202234113","https://openalex.org/W4306904969","https://openalex.org/W2101188133","https://openalex.org/W4248731570","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W4380318855"],"abstract_inverted_index":{"Incomplete":[0],"or":[1],"imprecise":[2],"models":[3],"of":[4,83,99,119,128,145,157],"control":[5,21,76,85,100,105],"systems":[6],"make":[7],"it":[8],"difficult":[9],"to":[10,38,49,68,102,115,161],"find":[11],"an":[12],"appropriate":[13],"structure":[14,86],"and":[15,87,93],"parameter":[16,123],"set":[17,124],"for":[18,107,141],"a":[19,46,58,70,113,121,129,138,149],"corresponding":[20],"policy.":[22,77,147],"These":[23],"problems":[24],"are":[25],"addressed":[26],"by":[27,44],"reinforcement":[28],"learning":[29],"algorithms":[30],"like":[31],"policy":[32,41,60],"gradient":[33,42],"methods.":[34],"We":[35,63],"describe":[36],"how":[37],"stabilise":[39],"the":[40,51,65,75,84,104,116,126,143,146,155,158],"descent":[43],"introducing":[45],"regularisation":[47],"term":[48],"enhance":[50],"episodic":[52],"natural":[53],"actor-critic":[54],"approach.":[55],"This":[56,78],"allows":[57],"more":[59],"independent":[61],"usage.":[62],"used":[64],"resulting":[66],"algorithm":[67],"optimise":[69],"z-transformed":[71],"rational":[72],"function":[73],"representing":[74],"representation":[79],"facilitates":[80],"simultaneous":[81],"optimisation":[82],"its":[88],"parameters":[89],"in":[90,97],"time":[91],"space":[92],"can":[94],"be":[95],"analysed":[96],"terms":[98],"theory":[101],"predict":[103],"behaviour":[106],"arbitrary":[108],"scenarios.":[109,166],"Furthermore":[110],"we":[111],"present":[112],"solution":[114],"general":[117],"problem":[118],"finding":[120],"initial":[122],"with":[125,163],"help":[127],"single":[130],"demonstrated":[131],"trajectory.":[132],"The":[133],"approach":[134,160],"is":[135],"evaluated":[136],"on":[137],"cartpole":[139],"simulation":[140],"demonstrating":[142],"expressiveness":[144],"Furthermore,":[148],"real":[150,164],"soccer":[151],"robot":[152],"scenario":[153],"demonstrates":[154],"ability":[156],"proposed":[159],"deal":[162],"world":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}