{"id":"https://openalex.org/W7095585622","doi":null,"title":"Solving partially observable reinforcement learning problems with recurrent neural networks","display_name":"Solving partially observable reinforcement learning problems with recurrent neural networks","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W7095585622"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.3718","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.3718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.hut.fi/ECML2005/finalpapers/SchaferUdluft.pdf","raw_type":"text"},"volume":null,"type":"article","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":false,"raw_author_name":"Anton Maximilian Sch\u00e4fer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591","observed_orcids":["https://orcid.org/0000-0002-5767-2591"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Departement Neural Computation","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Departement Neural Computation","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.52616113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10320","display_name":"Neural Networks and Applications","score":0.0,"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":0.0,"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/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9190000295639038},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.875},{"id":"https://openalex.org/keywords/phase-space-reconstruction","display_name":"phase space reconstruction","score":0.6340000033378601},{"id":"https://openalex.org/keywords/cart-pole-problem","display_name":"cart-pole problem","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7903000116348267},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7688999772071838},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7559999823570251},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6761999726295471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686000227928162},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.621999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555899977684021},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C2985963534","wikidata":"https://www.wikidata.org/wiki/Q7603704","display_name":"State information","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.3718","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.3718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.hut.fi/ECML2005/finalpapers/SchaferUdluft.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7221510620","https://openalex.org/W4413766826","https://openalex.org/W122144300","https://openalex.org/W2173087131","https://openalex.org/W2137096508","https://openalex.org/W2290302229","https://openalex.org/W2295700201","https://openalex.org/W2146763310","https://openalex.org/W4388574051","https://openalex.org/W2793100723"],"abstract_inverted_index":{"Abstract.":[0],"In":[1,36,68,83],"partially":[2,65],"observable":[3,100],"environments":[4],"effective":[5],"reinforcement":[6,129,156],"learning":[7,130,144,157],"(RL)":[8],"is":[9,159,166],"still":[10],"a":[11,51,69,74,120,194],"fairly":[12],"open":[13],"question.":[14],"Most":[15],"common":[16],"algorithms":[17],"fail":[18],"to":[19,48,78,92,127,161,168,175,212],"produce":[20],"good":[21],"results":[22,192],"for":[23],"those":[24,33],"problems.":[25,131],"However,":[26],"many":[27],"real-world":[28],"applications":[29],"are":[30,109,119,173],"characterized":[31],"by":[32,179],"difficult":[34],"environments.":[35],"this":[37,210],"paper":[38],"we":[39,72,86,133,205],"propose":[40],"the":[41,54,59,63,79,88,137,155,169,197,202,207],"application":[42],"of":[43,58,62,90,115,140,154,196,209],"recurrent":[44],"neural":[45,142],"networks":[46],"(RNN)":[47],"identify":[49,93],"in":[50],"first":[52,203],"step":[53,71],"complete":[55],"state":[56,81,111],"space":[57,112],"environment":[60],"out":[61],"only":[64,151],"available":[66],"information.":[67],"second":[70],"apply":[73],"standard":[75],"RL":[76],"algorithm":[77],"reconstructed":[80],"space.":[82],"doing":[84],"so":[85],"use":[87],"capability":[89],"RNNs":[91,108,118],"and":[94,123,145,186],"simulate":[95],"any":[96],"dynamical":[97],"system.":[98],"Partially":[99],"Markov":[101],"decision":[102],"processes":[103],"(POMDPs)":[104],"as":[105,107],"well":[106],"both":[110],"models.":[113],"Out":[114],"that":[116,150,171],"reason":[117],"very":[121],"appropriate":[122],"even":[124],"obvious":[125],"method":[126],"model":[128],"Further":[132],"can":[134],"profit":[135],"from":[136],"wide":[138],"range":[139],"wellestablished":[141],"network":[143],"optimization":[146],"methods.":[147],"We":[148,188],"show":[149],"minimum":[152],"information":[153,178],"problem":[158],"needed":[160],"achieve":[162],"remarkable":[163],"results.":[164],"This":[165],"due":[167],"fact,":[170],"RNN":[172],"able":[174],"compensate":[176],"missing":[177],"building":[180],"up":[181],"their":[182],"own":[183],"internal":[184],"dynamics":[185],"memory.":[187],"demonstrate":[189],"our":[190],"theoretical":[191],"on":[193],"variation":[195],"well-known":[198],"cart-pole":[199],"problem.":[200],"For":[201],"time":[204],"reduce":[206],"observability":[208],"example":[211],"one":[213],"single":[214],"variable.":[215],"1":[216]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}