{"id":"https://openalex.org/W4402800273","doi":"https://doi.org/10.1145/3696112","title":"Scaling Learning-based Policy Optimization for Temporal Logic Tasks by Controller Network Dropout","display_name":"Scaling Learning-based Policy Optimization for Temporal Logic Tasks by Controller Network Dropout","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402800273","doi":"https://doi.org/10.1145/3696112"},"language":"en","primary_location":{"id":"doi:10.1145/3696112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696112","pdf_url":null,"source":{"id":"https://openalex.org/S2506189754","display_name":"ACM Transactions on Cyber-Physical Systems","issn_l":"2378-962X","issn":["2378-962X","2378-9638"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Cyber-Physical Systems","raw_type":"journal-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/A5054637010","display_name":"Navid Hashemi","orcid":"https://orcid.org/0000-0002-6147-3675"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Navid Hashemi","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-6147-3675","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044251694","display_name":"Bardh Hoxha","orcid":"https://orcid.org/0000-0001-6255-7566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bardh Hoxha","raw_affiliation_strings":["Toyota NA R&D, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0001-6255-7566","affiliations":[{"raw_affiliation_string":"Toyota NA R&D, Ann Arbor, Michigan, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061971606","display_name":"Danil Prokhorov","orcid":"https://orcid.org/0000-0002-6208-4233"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danil Prokhorov","raw_affiliation_strings":["Toyota NA R&D, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0002-6208-4233","affiliations":[{"raw_affiliation_string":"Toyota NA R&D, Ann Arbor, Michigan, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058732387","display_name":"Georgios Fainekos","orcid":"https://orcid.org/0000-0002-0456-2129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Fainekos","raw_affiliation_strings":["Toyota NA R&D, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0002-0456-2129","affiliations":[{"raw_affiliation_string":"Toyota NA R&D, Ann Arbor, Michigan, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057473400","display_name":"Jyotirmoy V. Deshmukh","orcid":"https://orcid.org/0000-0003-4683-5540"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyotirmoy V. Deshmukh","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-4683-5540","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9614,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7863149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"8","issue":"4","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11424","display_name":"Security and Verification in Computing","score":0.9945999979972839,"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/dropout","display_name":"Dropout (neural networks)","score":0.8358321785926819},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6361478567123413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5538432598114014},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4689466655254364},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.452808141708374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38568034768104553},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3730011284351349},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3424435257911682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2600977420806885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1550079882144928}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.8358321785926819},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6361478567123413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5538432598114014},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4689466655254364},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.452808141708374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38568034768104553},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3730011284351349},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3424435257911682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2600977420806885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1550079882144928},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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},{"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:10.1145/3696112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696112","pdf_url":null,"source":{"id":"https://openalex.org/S2506189754","display_name":"ACM Transactions on Cyber-Physical Systems","issn_l":"2378-962X","issn":["2378-962X","2378-9638"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Cyber-Physical Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W117556101","https://openalex.org/W605243474","https://openalex.org/W1506101803","https://openalex.org/W1533557569","https://openalex.org/W1547304883","https://openalex.org/W1553101044","https://openalex.org/W1935692274","https://openalex.org/W1979297612","https://openalex.org/W1980569135","https://openalex.org/W1981276685","https://openalex.org/W2023808162","https://openalex.org/W2026629052","https://openalex.org/W2038834149","https://openalex.org/W2048846187","https://openalex.org/W2064572756","https://openalex.org/W2071797744","https://openalex.org/W2078151802","https://openalex.org/W2092884371","https://openalex.org/W2095274657","https://openalex.org/W2095705004","https://openalex.org/W2131399618","https://openalex.org/W2145970716","https://openalex.org/W2151958719","https://openalex.org/W2163602945","https://openalex.org/W2167799541","https://openalex.org/W2254640530","https://openalex.org/W2331143823","https://openalex.org/W2470448410","https://openalex.org/W2529490754","https://openalex.org/W2560504659","https://openalex.org/W2567705466","https://openalex.org/W2594675090","https://openalex.org/W2612690371","https://openalex.org/W2621540998","https://openalex.org/W2624912704","https://openalex.org/W2765982206","https://openalex.org/W2776485332","https://openalex.org/W2792781634","https://openalex.org/W2803455449","https://openalex.org/W2841721725","https://openalex.org/W2963231286","https://openalex.org/W2963778636","https://openalex.org/W2971273347","https://openalex.org/W2976205474","https://openalex.org/W2979818850","https://openalex.org/W2998402843","https://openalex.org/W3004091789","https://openalex.org/W3034174753","https://openalex.org/W3046272654","https://openalex.org/W3046650501","https://openalex.org/W3090827750","https://openalex.org/W3095983813","https://openalex.org/W3101375348","https://openalex.org/W3103644807","https://openalex.org/W3120924814","https://openalex.org/W3164776375","https://openalex.org/W3183867501","https://openalex.org/W3184555489","https://openalex.org/W3185432324","https://openalex.org/W3185714178","https://openalex.org/W3199810006","https://openalex.org/W3200011036","https://openalex.org/W4229029576","https://openalex.org/W4292249799","https://openalex.org/W4296963693","https://openalex.org/W4304547391","https://openalex.org/W4311414009","https://openalex.org/W4323927861","https://openalex.org/W4368408193","https://openalex.org/W4391020705","https://openalex.org/W4400518895","https://openalex.org/W4401810328","https://openalex.org/W6683991275","https://openalex.org/W6846015771"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W2782041652","https://openalex.org/W2612657834","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W1987310671","https://openalex.org/W2952088488","https://openalex.org/W1521968289","https://openalex.org/W4225691210","https://openalex.org/W4399568863"],"abstract_inverted_index":{"This":[0,150],"article":[1],"introduces":[2],"a":[3,16,52,70,73,109,152,184,233],"model-based":[4],"approach":[5,277],"for":[6,10,49,114,248],"training":[7,128,235],"feedback":[8,104,117],"controllers":[9],"an":[11,87],"autonomous":[12],"agent":[13,31],"operating":[14],"in":[15,41,217,220,232],"highly":[17],"non-linear":[18],"(albeit":[19],"deterministic)":[20],"environment.":[21],"We":[22,102,119,237,271],"desire":[23],"the":[24,30,79,92,95,100,116,134,142,146,175,191,200,204,214,221,225,230,273],"trained":[25],"policy":[26],"to":[27,127,141,157,167,252],"ensure":[28],"that":[29,60,239],"satisfies":[32],"specific":[33],"task":[34,53,148,170,222],"objectives":[35,171],"and":[36,72,94,106,159,162,265,286],"safety":[37],"constraints,":[38],"both":[39],"expressed":[40],"Discrete-Time":[42],"Signal":[43],"Temporal":[44],"Logic":[45],"(DT-STL).":[46],"One":[47,198],"advantage":[48],"reformulation":[50],"of":[51,97,136,145,193,199,206,275,292],"via":[54],"formal":[55],"frameworks,":[56],"like":[57],"DT-STL,":[58],"is":[59,125,139,203],"it":[61],"permits":[62],"quantitative":[63],"satisfaction":[64],"semantics.":[65],"In":[66],"other":[67],"words,":[68],"given":[69],"trajectory":[71,93],"DT-STL":[74],"formula,":[75],"we":[76,107,182,212],"can":[77,83,244],"compute":[78],"robustness":[80],",":[81,210],"which":[82],"be":[84,245],"interpreted":[85],"as":[86],"approximate":[88,213],"signed":[89],"distance":[90],"between":[91],"set":[96],"trajectories":[98,266],"satisfying":[99],"formula.":[101],"utilize":[103],"control,":[105],"assume":[108],"feed":[110],"forward":[111],"neural":[112,130],"network":[113,208],"learning":[115,123],"controller.":[118],"show":[120,238],"how":[121],"this":[122,180],"problem":[124],"similar":[126],"recurrent":[129,137],"networks":[131],"(RNNs),":[132],"where":[133,211],"number":[135],"units":[138],"proportional":[140],"temporal":[143],"horizon":[144,223],"agent\u2019s":[147],"objectives.":[149],"poses":[151],"challenge:":[153],"RNNs":[154],"are":[155],"susceptible":[156],"vanishing":[158],"exploding":[160],"gradients,":[161],"na\u00efve":[163],"gradient":[164,186,196,250],"descent-based":[165],"strategies":[166],"solve":[168],"long-horizon":[169],"thus":[172],"suffer":[173],"from":[174],"same":[176],"problems.":[177],"To":[178],"address":[179],"challenge,":[181],"introduce":[183],"novel":[185],"approximation":[187],"algorithm":[188],"based":[189],"on":[190,278],"idea":[192],"dropout":[194,209],"or":[195],"sampling.":[197],"main":[201],"contributions":[202],"notion":[205],"controller":[207,216,231],"NN":[215],"several":[218],"timesteps":[219],"by":[224],"control":[226,241],"input":[227],"obtained":[228],"using":[229],"previous":[234],"step.":[236],"our":[240,276],"synthesis":[242],"methodology":[243],"quite":[246],"helpful":[247],"stochastic":[249],"descent":[251],"converge":[253],"with":[254],"less":[255],"numerical":[256],"issues,":[257],"enabling":[258],"scalable":[259],"back-propagation":[260],"over":[261,267,290],"longer":[262],"time":[263],"horizons":[264],"higher-dimensional":[268],"state":[269],"spaces.":[270],"demonstrate":[272],"efficacy":[274],"various":[279],"motion":[280],"planning":[281],"applications":[282],"requiring":[283],"complex":[284],"spatio-temporal":[285],"sequential":[287],"tasks":[288],"ranging":[289],"thousands":[291],"timesteps.":[293]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}