{"id":"https://openalex.org/W2103061585","doi":"https://doi.org/10.1109/ijcnn.2008.4633888","title":"A memory-based reinforcement learning algorithm for partially observable Markovian decision processes","display_name":"A memory-based reinforcement learning algorithm for partially observable Markovian decision processes","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2103061585","doi":"https://doi.org/10.1109/ijcnn.2008.4633888","mag":"2103061585"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2008.4633888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4633888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","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/A5028544958","display_name":"Lei Zheng","orcid":"https://orcid.org/0000-0002-8603-0096"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Lei Zheng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore#TAB#","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006841849","display_name":"Siu\u2010Yeung Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siu-Yeung Cho","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore#TAB#","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063229067","display_name":"Chai Quek","orcid":"https://orcid.org/0000-0002-7313-4339"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chai Quek","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore#TAB#","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028544958"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.5721,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78399714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"4","issue":null,"first_page":"800","last_page":"805"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9821000099182129,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9591000080108643,"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-process","display_name":"Partially observable Markov decision process","score":0.8921170234680176},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8484908938407898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7377630472183228},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.669013500213623},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6123343110084534},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5687086582183838},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5440508723258972},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49534597992897034},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4933282434940338},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4861745238304138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.415221631526947},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39197492599487305},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2883976399898529},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2678184509277344},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.19807249307632446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16753071546554565}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8921170234680176},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8484908938407898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7377630472183228},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.669013500213623},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6123343110084534},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5687086582183838},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5440508723258972},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49534597992897034},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4933282434940338},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4861745238304138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.415221631526947},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39197492599487305},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2883976399898529},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2678184509277344},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.19807249307632446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16753071546554565},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2008.4633888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4633888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2098432798","https://openalex.org/W2101242010","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2169294731","https://openalex.org/W2170120409","https://openalex.org/W2341171179","https://openalex.org/W3139460557","https://openalex.org/W4214717370","https://openalex.org/W6675043515","https://openalex.org/W6792366008"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"This":[0,78],"paper":[1,79,86],"presents":[2],"a":[3,11,37,131],"modified":[4],"version":[5],"of":[6,39,91,152],"U-tree":[7,56,127],"(A.K.":[8],"McCallum,":[9],"1996),":[10],"memory-based":[12],"reinforcement":[13],"learning":[14],"(RL)":[15],"algorithm":[16,114],"that":[17,89],"uses":[18],"selective":[19],"perception":[20],"and":[21,94,105,146],"short-term":[22],"memory":[23],"to":[24,42,61,107,119],"handle":[25],"partially":[26],"observable":[27],"Markovian":[28],"decision":[29],"processes":[30],"(POMDP).":[31],"Conventional":[32],"RL":[33],"algorithms":[34],"rely":[35],"on":[36,74],"set":[38],"pre-defined":[40],"states":[41],"model":[43,70,82,98],"the":[44,51,68,92,109,139,150,153],"environment,":[45],"even":[46],"though":[47],"it":[48,64,102],"can":[49,65],"learn":[50],"state":[52,69,97],"transitions":[53],"from":[54],"experience.":[55],"is":[57,103,128],"not":[58],"only":[59],"able":[60],"do":[62],"that,":[63],"also":[66,87],"build":[67],"by":[71,100],"itself":[72],"based":[73],"raw":[75],"sensor":[76],"inputs.":[77],"enhances":[80],"U-Treepsilas":[81],"generation":[83],"process.":[84],"The":[85,125],"shows":[88],"because":[90],"simplified":[93],"yet":[95],"effective":[96],"generated":[99],"U-tree,":[101],"feasible":[104],"preferable":[106],"adopt":[108],"classical":[110],"dynamic":[111],"programming":[112],"(DP)":[113],"for":[115],"average":[116],"reward":[117],"MDP":[118],"solve":[120],"some":[121],"difficult":[122],"POMDP":[123],"problems.":[124],"new":[126],"tested":[129],"using":[130],"car-driving":[132],"task":[133],"with":[134,138],"31,224":[135],"world":[136],"states,":[137],"agent":[140],"having":[141],"very":[142],"limited":[143],"sensory":[144],"information":[145],"little":[147],"knowledge":[148],"about":[149],"dynamics":[151],"environment.":[154]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}