{"id":"https://openalex.org/W2163908189","doi":null,"title":"Transition Point Dynamic Programming","display_name":"Transition Point Dynamic Programming","publication_year":1993,"publication_date":"1993-11-29","ids":{"openalex":"https://openalex.org/W2163908189","mag":"2163908189"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.981.5902","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.981.5902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/848-transition-point-dynamic-programming.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/A5029510021","display_name":"Kenneth M. Buckland","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kenneth M. Buckland","raw_affiliation_strings":["PMC-Sierra Inc., Burnaby, B.C., Canada and Dept. of Electrical Engineering, University of British Columbia, Vancouver, B.C, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PMC-Sierra Inc., Burnaby, B.C., Canada and Dept. of Electrical Engineering, University of British Columbia, Vancouver, B.C, Canada#TAB#","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109983941","display_name":"Peter D. Lawrence","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peter D. Lawrence","raw_affiliation_strings":["Department of Electrical Engineering, University of British Columbia, Vancouver, B.C., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of British Columbia, Vancouver, B.C., Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":0.401,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.59216342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":"6","issue":null,"first_page":"639","last_page":"646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7231000065803528,"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":0.7231000065803528,"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":0.27639999985694885,"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/T10791","display_name":"Advanced Control Systems Optimization","score":9.999999747378752e-05,"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/adaptive-optimal-control","display_name":"adaptive optimal control","score":0.8289999961853027},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6299999952316284},{"id":"https://openalex.org/keywords/state-space-exploration","display_name":"state space exploration","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.7981603145599365},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7310677766799927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640328168869019},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5642541646957397},{"id":"https://openalex.org/C2993627981","wikidata":"https://www.wikidata.org/wiki/Q7456295","display_name":"Set point","level":2,"score":0.475276380777359},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.46940934658050537},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.44396835565567017},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4401256740093231},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43839845061302185},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4350038468837738},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43166983127593994},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42109423875808716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27346867322921753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2689628005027771},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18891975283622742},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.15082934498786926},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13158473372459412},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07859832048416138},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.981.5902","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.981.5902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/848-transition-point-dynamic-programming.pdf","raw_type":"text"},{"id":"mag:2163908189","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/848-transition-point-dynamic-programming.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","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":6,"referenced_works":["https://openalex.org/W111328409","https://openalex.org/W1640646391","https://openalex.org/W1946098947","https://openalex.org/W2140366636","https://openalex.org/W2319287212","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W7051524171","https://openalex.org/W2128831926","https://openalex.org/W6614468","https://openalex.org/W2617439680","https://openalex.org/W7100048524","https://openalex.org/W1843985569","https://openalex.org/W4312199098","https://openalex.org/W6999959684","https://openalex.org/W7005961664","https://openalex.org/W2821609474"],"abstract_inverted_index":{"Transition":[0],"point":[1],"dynamic":[2,11,34],"programming":[3,12],"(TPDP)":[4],"is":[5],"a":[6,68,91],"memory-based,":[7],"reinforcement":[8],"learning,":[9],"direct":[10],"ap-proach":[13],"to":[14,61,72,90,109],"adaptive":[15],"optimal":[16,57,98],"control":[17,30,52,99],"that":[18],"can":[19],"reduce":[20],"the":[21,29,51,74,85,97],"learning":[22],"time":[23],"and":[24,79,106],"memory":[25],"usage":[26],"required":[27],"for":[28,56],"of":[31,44,70,76],"continuous":[32],"stochastic":[33],"systems.":[35],"TPDP":[36,59,95],"does":[37],"so":[38,111],"by":[39,66],"determining":[40],"an":[41,62],"ideal":[42,63],"set":[43,65],"transition":[45],"points":[46],"(TPs)":[47],"which":[48],"specify":[49],"only":[50],"action":[53],"changes":[54],"necessary":[55],"control.":[58],"converges":[60],"TP":[64],"using":[67,112],"variation":[69],"Q-Iearning":[71],"assess":[73],"mer-its":[75],"adding,":[77],"swapping":[78],"removing":[80],"TPs":[81],"from":[82],"states":[83],"throughout":[84],"state":[86],"space.":[87],"When":[88],"applied":[89],"race":[92],"track":[93],"problem,":[94],"learned":[96],"policy":[100],"much":[101],"sooner":[102],"than":[103],"conventional":[104],"Q-Iearning,":[105],"was":[107],"able":[108],"do":[110],"less":[113],"memory.":[114],"1":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}