{"id":"https://openalex.org/W2397792207","doi":null,"title":"Reinforcement Learning with Recurrent Neural Networks","display_name":"Reinforcement Learning with Recurrent Neural Networks","publication_year":2008,"publication_date":"2008-11-20","ids":{"openalex":"https://openalex.org/W2397792207","mag":"2397792207"},"language":"en","primary_location":{"id":"pmh:oai:osnadocs.ub.uni-osnabrueck.de:urn:nbn:de:gbv:700-2008112111","doi":null,"is_oa":false,"landing_page_url":"https://repositorium.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-2008112111","pdf_url":null,"source":{"id":"https://openalex.org/S4377196933","display_name":"osnaDocs (Osnabr\u00fcck University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170658231","host_organization_name":"Osnabr\u00fcck University","host_organization_lineage":["https://openalex.org/I170658231"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:doctoralThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5031325499","display_name":"Anton Maximilian Sch\u00e4fer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anton Maximilian Sch\u00e4fer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5031325499"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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":0.001500000013038516,"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/T10320","display_name":"Neural Networks and Applications","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.8539999723434448},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9679999947547913},{"id":"https://openalex.org/keywords/system-identification","display_name":"system identification","score":0.7300000190734863},{"id":"https://openalex.org/keywords/optimal-policy","display_name":"optimal policy","score":0.5580000281333923},{"id":"https://openalex.org/keywords/data-efficient-learning","display_name":"data-efficient learning","score":0.6330000162124634},{"id":"https://openalex.org/keywords/universal-approximation","display_name":"universal approximation","score":0.6380000114440918},{"id":"https://openalex.org/keywords/long-term-dependencies","display_name":"long-range dependencies","score":0.9120000004768372},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.8679999709129333},{"id":"https://openalex.org/keywords/gas-turbine-control","display_name":"gas turbine control","score":0.9160000085830688},{"id":"https://openalex.org/keywords/high-dimensional-dynamical-systems","display_name":"high-dimensional dynamical systems","score":0.777999997138977},{"id":"https://openalex.org/keywords/continuous-state-action-spaces","display_name":"continuous state and action spaces","score":0.75}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7437512874603271},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5302262902259827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4712579548358917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4168757200241089},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41365110874176025},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3103381097316742},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0732346773147583}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:osnadocs.ub.uni-osnabrueck.de:urn:nbn:de:gbv:700-2008112111","doi":null,"is_oa":false,"landing_page_url":"https://repositorium.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-2008112111","pdf_url":null,"source":{"id":"https://openalex.org/S4377196933","display_name":"osnaDocs (Osnabr\u00fcck University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170658231","host_organization_name":"Osnabr\u00fcck University","host_organization_lineage":["https://openalex.org/I170658231"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:doctoralThesis"},{"id":"pmh:oai:repositorium.ub.uni-osnabrueck.de:urn:nbn:de:gbv:700-2008112111","doi":null,"is_oa":false,"landing_page_url":"https://repositorium.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-2008112111","pdf_url":null,"source":{"id":"https://openalex.org/S4377196933","display_name":"osnaDocs (Osnabr\u00fcck University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170658231","host_organization_name":"Osnabr\u00fcck University","host_organization_lineage":["https://openalex.org/I170658231"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:doctoralThesis"},{"id":"mag:2397792207","doi":null,"is_oa":false,"landing_page_url":"http://repositorium.uni-osnabrueck.de/bitstream/urn%3Anbn%3Ade%3Agbv%3A700-2008112111/2/E-Diss839_thesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W3207342693"],"related_works":["https://openalex.org/W2006278461","https://openalex.org/W7097059499","https://openalex.org/W3124981469","https://openalex.org/W1570106308","https://openalex.org/W2894592470","https://openalex.org/W2143770247","https://openalex.org/W2884288476","https://openalex.org/W1997933491","https://openalex.org/W4399721942","https://openalex.org/W2949942850"],"abstract_inverted_index":{"Controlling":[0],"a":[1,12,17,21,79,117,160,195,231,272],"high-dimensional":[2],"dynamical":[3,108,140,171],"system":[4,245],"with":[5],"continuous":[6],"state":[7,147,223],"and":[8,34,106,125,209,247],"action":[9],"spaces":[10],"in":[11,70,110,142,181,253],"partially":[13],"unknown":[14],"environment":[15],"like":[16],"gas":[18,293],"turbine":[19,294],"is":[20,58,82,94,162,175,202,227],"challenging":[22],"problem.":[23],"So":[24],"far":[25],"often":[26,185],"hard":[27],"coded":[28],"rules":[29],"based":[30],"on":[31,279],"experts\u00b4":[32],"knowledge":[33],"experience":[35],"are":[36,48,76,113,131,277,287],"used.":[37],"Machine":[38],"learning":[39,102,127],"techniques,":[40],"which":[41,81],"comprise":[42],"the":[43,89,137,215,220,225,264],"field":[44],"of":[45,92,139,144,169,224,249,271,292,296],"reinforcement":[46,101,126,199],"learning,":[47,200],"generally":[49],"only":[50],"applied":[51,288],"to":[52,66,104,154,183,190,258,289],"sub-problems.":[53],"A":[54],"reason":[55],"for":[56,84,136,164,233],"this":[57,97],"that":[59,178,204],"most":[60,85,259],"standard":[61,234,281],"RL":[62,235,260],"approaches":[63,103],"still":[64],"fail":[65],"produce":[67],"satisfactory":[68],"results":[69],"those":[71],"complex":[72],"environments.":[73],"Besides,":[74],"they":[75,134,151,179,286],"rarely":[77],"data-efficient,":[78],"fact":[80],"crucial":[83],"real-world":[86],"applications,":[87],"where":[88],"available":[90],"amount":[91],"data":[93],"limited.":[95],"In":[96,158,214,256,284],"thesis":[98],"recurrent":[99,121,240],"neural":[100,122,242],"identify":[105],"control":[107,241],"systems":[109,141],"discrete":[111],"time":[112],"presented.":[114],"They":[115],"form":[116,143],"novel":[118],"connection":[119],"between":[120],"networks":[123],"(RNN)":[124],"(RL)":[128],"techniques.":[129],"RNN":[130,205,218],"used":[132,229],"as":[133,230],"allow":[135],"identification":[138,246],"high-dimensional,":[145],"non-linear":[146],"space":[148],"models.":[149],"Also,":[150],"have":[152],"shown":[153,203],"be":[155],"very":[156],"data-efficient.":[157],"addition,":[159,285],"proof":[161],"given":[163],"their":[165],"universal":[166],"approximation":[167],"capability":[168],"open":[170],"systems.":[172],"Moreover,":[173],"it":[174,201,262],"pointed":[176],"out":[177],"are,":[180],"contrast":[182,257],"an":[184,250],"cited":[186],"statement,":[187],"well":[188,207],"able":[189],"capture":[191],"long-term":[192],"dependencies.":[193],"As":[194],"first":[196],"step":[197],"towards":[198],"can":[206],"map":[208],"reconstruct":[210],"(partially":[211],"observable)":[212],"MDP.":[213],"so-called":[216],"hybrid":[217],"approach,":[219],"resulting":[221],"inner":[222],"network":[226,243],"then":[228],"basis":[232],"algorithms.":[236],"The":[237,275],"further":[238],"developed":[239],"combines":[244],"determination":[248],"optimal":[251,265],"policy":[252,266],"one":[254],"network.":[255],"methods,":[261],"determines":[263],"directly":[267],"without":[268],"making":[269],"use":[270],"value":[273],"function.":[274],"methods":[276],"tested":[278],"several":[280],"benchmark":[282],"problems.":[283],"different":[290],"kinds":[291],"simulations":[295],"industrial":[297],"scale.":[298]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}