{"id":"https://openalex.org/W2931553127","doi":"https://doi.org/10.1145/3302509.3311053","title":"Reduced variance deep reinforcement learning with temporal logic specifications","display_name":"Reduced variance deep reinforcement learning with temporal logic specifications","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2931553127","doi":"https://doi.org/10.1145/3302509.3311053","mag":"2931553127"},"language":"en","primary_location":{"id":"doi:10.1145/3302509.3311053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3302509.3311053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM/IEEE International Conference on Cyber-Physical Systems","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/A5076201548","display_name":"Qitong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qitong Gao","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065979443","display_name":"Davood Hajinezhad","orcid":"https://orcid.org/0000-0003-1733-0295"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Davood Hajinezhad","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456327","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-8561-5092"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014874021","display_name":"Yiannis Kantaros","orcid":"https://orcid.org/0000-0002-0257-7378"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiannis Kantaros","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080808780","display_name":"Michael M. Zavlanos","orcid":"https://orcid.org/0000-0003-1748-8228"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Zavlanos","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":4.1943,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95235507,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"237","last_page":"248"},"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/T10142","display_name":"Formal Methods in Verification","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9883999824523926,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8797136545181274},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7884634733200073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688752174377441},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5824210047721863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47452035546302795},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4708658754825592},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4653625786304474},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4504920542240143},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4458669424057007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20936375856399536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8797136545181274},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7884634733200073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688752174377441},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5824210047721863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47452035546302795},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4708658754825592},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4653625786304474},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4504920542240143},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4458669424057007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20936375856399536},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3302509.3311053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3302509.3311053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM/IEEE International Conference on Cyber-Physical Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1498432697","https://openalex.org/W1576452626","https://openalex.org/W1791038712","https://openalex.org/W1971086298","https://openalex.org/W1988720110","https://openalex.org/W2009797711","https://openalex.org/W2059470663","https://openalex.org/W2075268401","https://openalex.org/W2077578897","https://openalex.org/W2078151802","https://openalex.org/W2103728338","https://openalex.org/W2107438106","https://openalex.org/W2117341272","https://openalex.org/W2121863487","https://openalex.org/W2131600418","https://openalex.org/W2134042548","https://openalex.org/W2134130436","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2290354866","https://openalex.org/W2301983558","https://openalex.org/W2306875213","https://openalex.org/W2567705466","https://openalex.org/W2570983198","https://openalex.org/W2594675090","https://openalex.org/W2620827312","https://openalex.org/W2624912704","https://openalex.org/W2746553466","https://openalex.org/W2787259794","https://openalex.org/W2797302609","https://openalex.org/W2798923485","https://openalex.org/W2914304175","https://openalex.org/W2949117887","https://openalex.org/W2952215077","https://openalex.org/W2953302092","https://openalex.org/W2963117388","https://openalex.org/W2963778636","https://openalex.org/W2964037929","https://openalex.org/W3003754596","https://openalex.org/W4226221853"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3115089987","https://openalex.org/W2089415692","https://openalex.org/W2359964334","https://openalex.org/W2937181779","https://openalex.org/W4308702637","https://openalex.org/W1556532828","https://openalex.org/W1985560493","https://openalex.org/W2182304831","https://openalex.org/W1511927616"],"abstract_inverted_index":{"In":[0,197],"this":[1,229],"paper,":[2],"we":[3,35],"propose":[4],"a":[5,37,59,90,96,164],"model-free":[6,233],"reinforcement":[7,126,235],"learning":[8,156,236],"method":[9,129,152],"to":[10,49,83,111,178],"synthesize":[11,240],"control":[12,203],"policies":[13,204,241],"for":[14,266],"mobile":[15],"robots":[16],"modeled":[17,189],"as":[18,270,272],"Markov":[19],"Decision":[20],"Process":[21],"(MDP)":[22],"with":[23,95,108,208],"unknown":[24,136],"transition":[25,158],"probabilities":[26,159],"that":[27,43,62,74,120,218,238,242,275],"satisfy":[28],"Linear":[29],"Temporal":[30],"Logic":[31],"(LTL)":[32],"specifications.":[33,222],"Specifically,":[34],"develop":[36,100],"reduced":[38,105],"variance":[39,106],"deep":[40,86,125,234],"Q-Learning":[41,87],"technique":[42],"relies":[44],"on":[45,64],"Neural":[46],"Networks":[47],"(NN)":[48],"approximate":[50],"the":[51,55,65,69,76,85,132,144,147,157,161,176,185,198,201,206,210,216,220,224,231,244,267],"state-action":[52],"values":[53],"of":[54,68,134,146,226,246,262],"MDP":[56],"and":[57,99,141,260],"employs":[58],"reward":[60],"function":[61,138],"depends":[63],"accepting":[66],"condition":[67],"Deterministic":[70],"Rabin":[71],"Automaton":[72],"(DRA)":[73],"captures":[75],"LTL":[77,249],"specification.":[78],"The":[79],"key":[80],"idea":[81],"is":[82,230],"convert":[84],"problem":[88,94],"into":[89],"nonconvex":[91],"max-min":[92],"optimization":[93],"finite-sum":[97],"structure,":[98],"an":[101,135,180,248],"Arrow-Hurwicz-Uzawa":[102],"type":[103],"stochastic":[104],"algorithm":[107,237,269],"constant":[109],"stepsize":[110],"solve":[112],"it.":[113],"Unlike":[114],"Stochastic":[115],"Gradient":[116],"Descent":[117],"(SGD)":[118],"methods":[119],"are":[121,264],"often":[122],"used":[123],"in":[124,160,215],"learning,":[127],"our":[128,151,227,277],"can":[130,142,239],"estimate":[131],"gradients":[133],"loss":[137],"more":[139],"accurately":[140,190],"improve":[143],"stability":[145],"training":[148],"process.":[149],"Moreover,":[150],"does":[153],"not":[154,195,255],"require":[155],"MDP,":[162,166],"constructing":[163],"product":[165],"or":[167,191],"computing":[168],"Accepting":[169],"Maximal":[170],"End":[171],"Components":[172],"(AMECs).":[173],"This":[174],"allows":[175],"robot":[177],"learn":[179],"optimal":[181],"policy":[182],"even":[183,251],"if":[184,192,252],"environment":[186],"cannot":[187],"be":[188],"AMECs":[193,253],"do":[194,254],"exist.":[196,256],"latter":[199],"case,":[200],"resulting":[202],"minimize":[205],"frequency":[207],"which":[209],"system":[211],"enters":[212],"bad":[213],"states":[214],"DRA":[217],"violate":[219],"task":[221],"To":[223],"best":[225],"knowledge,":[228],"first":[232],"maximize":[243],"probability":[245],"satisfying":[247],"specification":[250],"Rigorous":[257],"convergence":[258,263],"analysis":[259],"rate":[261],"provided":[265],"proposed":[268],"well":[271],"numerical":[273],"experiments":[274],"validate":[276],"method.":[278]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}