{"id":"https://openalex.org/W2249840556","doi":"https://doi.org/10.5555/2772879.2773385","title":"Trajectory Sampling Value Iteration: Improved Dyna Search for MDPs","display_name":"Trajectory Sampling Value Iteration: Improved Dyna Search for MDPs","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2249840556","doi":"https://doi.org/10.5555/2772879.2773385","mag":"2249840556"},"language":"en","primary_location":{"id":"mag:2249840556","doi":"https://doi.org/10.5555/2772879.2773385","is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/atal/aamas2015.html#ZhouLFZ15","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Adaptive Agents and Multi-Agents Systems","raw_type":null},"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/A5102797061","display_name":"Yicheng Zhou","orcid":"https://orcid.org/0000-0002-4491-0327","observed_orcids":["https://orcid.org/0000-0002-4491-0327"]},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Zhou","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4491-0327","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100666897","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0002-0941-8767","observed_orcids":["https://orcid.org/0000-0002-0941-8767","https://orcid.org/0009-0009-9967-9845"]},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0941-8767","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087429872","display_name":"Qiming Fu","orcid":"https://orcid.org/0000-0001-9757-4323","observed_orcids":["https://orcid.org/0000-0001-9757-4323","https://orcid.org/0009-0003-6788-3696"]},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiming Fu","raw_affiliation_strings":["[Suzhou University of Science and Technology, Suzhou, China]"],"raw_orcid":"https://orcid.org/0000-0001-9757-4323","affiliations":[{"raw_affiliation_string":"[Suzhou University of Science and Technology, Suzhou, China]","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747","observed_orcids":["https://orcid.org/0000-0002-9238-4747"]},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongzhang Zhang","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9238-4747","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2949,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65213491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1685","last_page":"1686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"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/T10906","display_name":"AI-based Problem Solving and Planning","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/value-iteration","display_name":"value iteration","score":0.7429999709129333},{"id":"https://openalex.org/keywords/trajectory-sampling","display_name":"trajectory sampling","score":0.9980000257492065},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8889999985694885},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.6520000100135803},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.703000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75043785572052},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6658461093902588},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5954858660697937},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5933674573898315},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5769873261451721},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5276966094970703},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4983646869659424},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4602344036102295},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.42684391140937805},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4194219708442688},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3555978834629059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3513377904891968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3489522933959961},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.24626293778419495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12683182954788208},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.10246726870536804},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08028843998908997},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2249840556","doi":"https://doi.org/10.5555/2772879.2773385","is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/atal/aamas2015.html#ZhouLFZ15","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Adaptive Agents and Multi-Agents Systems","raw_type":null},{"id":"mag:2461389619","doi":null,"is_oa":false,"landing_page_url":"http://www.aamas2015.com/en/AAMAS_2015_USB/aamas/p1685.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":3,"referenced_works":["https://openalex.org/W1714211023","https://openalex.org/W1980035368","https://openalex.org/W2153039919"],"related_works":["https://openalex.org/W2461389619","https://openalex.org/W1996627310","https://openalex.org/W7133188236","https://openalex.org/W2134461419","https://openalex.org/W2046669581","https://openalex.org/W2116901014","https://openalex.org/W116231174","https://openalex.org/W2519270595","https://openalex.org/W7124160083","https://openalex.org/W2134760705"],"abstract_inverted_index":{"Traditional":[0],"online":[1],"learning":[2,18,43],"algorithms":[3],"often":[4],"suffer":[5],"from":[6],"the":[7,27,42,58,66,82,94,119,123,130],"lack":[8],"of":[9,25,57,151],"convergence":[10,152],"rate":[11,153],"and":[12,122,146,154],"accuracy.":[13,155],"The":[14,29,49],"Dyna-2":[15,142],"framework,":[16],"combining":[17],"with":[19,97],"searching":[20],"methods,":[21],"provides":[22],"a":[23,37,54,88,98],"way":[24],"alleviating":[26],"problem.":[28],"main":[30],"idea":[31],"behind":[32],"it":[33],"is":[34,61,68,105],"to":[35,45,93,107,128],"execute":[36],"simulation-based":[38],"search":[39,50,95],"that":[40,60,139],"helps":[41],"process":[44,51,96],"select":[46],"better":[47,76],"actions.":[48],"relies":[52],"on":[53],"simulated":[55],"model":[56,67],"environment":[59],"built":[62],"during":[63],"learning.":[64],"However,":[65],"not":[69],"fully":[70],"used":[71,106],"in":[72,133,143,149],"Dyna-2.":[73],"To":[74],"provide":[75],"solution":[77],"quality,":[78],"our":[79],"paper":[80],"improves":[81],"algorithm":[83],"by":[84,113],"applying":[85],"value":[86],"iteration,":[87],"model-based":[89],"dynamic":[90,114],"programming":[91],"algorithm,":[92],"trajectory":[99],"sampling":[100,104],"approach":[101],"(DynaTSVI).":[102],"Trajectory":[103],"reduce":[108],"high":[109],"time":[110],"complexity":[111],"caused":[112],"programming.":[115],"Experimentally,":[116],"we":[117],"use":[118],"Dyna":[120],"Maze":[121],"Windy":[124],"Grid":[125],"World":[126],"tasks":[127],"analyze":[129],"proposed":[131],"method":[132],"several":[134],"aspects.":[135],"Our":[136],"results":[137],"show":[138],"DynaTSVI":[140],"outperforms":[141],"both":[144],"deterministic":[145],"stochastic":[147],"environments":[148],"terms":[150]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}