{"id":"https://openalex.org/W4382318883","doi":"https://doi.org/10.1609/aaai.v37i10.26407","title":"Learning Control Policies for Stochastic Systems with Reach-Avoid Guarantees","display_name":"Learning Control Policies for Stochastic Systems with Reach-Avoid Guarantees","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382318883","doi":"https://doi.org/10.1609/aaai.v37i10.26407"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v37i10.26407","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i10.26407","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26407/26179","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26407/26179","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041082080","display_name":"\u0110or\u0111e \u017dikeli\u0107","orcid":"https://orcid.org/0000-0002-4681-1699"},"institutions":[{"id":"https://openalex.org/I157556583","display_name":"Institute of Science and Technology Austria","ror":"https://ror.org/03gnh5541","country_code":"AT","type":"education","lineage":["https://openalex.org/I157556583"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"\u0110or\u0111e \u017dikeli\u0107","raw_affiliation_strings":["IST Austria"],"affiliations":[{"raw_affiliation_string":"IST Austria","institution_ids":["https://openalex.org/I157556583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036588940","display_name":"Mathias Lechner","orcid":"https://orcid.org/0000-0002-6117-0076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathias Lechner","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080555605","display_name":"Thomas A. Henzinger","orcid":"https://orcid.org/0000-0002-2985-7724"},"institutions":[{"id":"https://openalex.org/I157556583","display_name":"Institute of Science and Technology Austria","ror":"https://ror.org/03gnh5541","country_code":"AT","type":"education","lineage":["https://openalex.org/I157556583"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Thomas A. Henzinger","raw_affiliation_strings":["IST Austria"],"affiliations":[{"raw_affiliation_string":"IST Austria","institution_ids":["https://openalex.org/I157556583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052607806","display_name":"Krishnendu Chatterjee","orcid":"https://orcid.org/0000-0002-4561-241X"},"institutions":[{"id":"https://openalex.org/I157556583","display_name":"Institute of Science and Technology Austria","ror":"https://ror.org/03gnh5541","country_code":"AT","type":"education","lineage":["https://openalex.org/I157556583"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Krishnendu Chatterjee","raw_affiliation_strings":["IST Austria"],"affiliations":[{"raw_affiliation_string":"IST Austria","institution_ids":["https://openalex.org/I157556583"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041082080"],"corresponding_institution_ids":["https://openalex.org/I157556583"],"apc_list":null,"apc_paid":null,"fwci":2.2959,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89896907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"37","issue":"10","first_page":"11926","last_page":"11935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9207000136375427,"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":0.9207000136375427,"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/computer-science","display_name":"Computer science","score":0.743329644203186},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6705431938171387},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.5817328691482544},{"id":"https://openalex.org/keywords/certificate","display_name":"Certificate","score":0.5049083828926086},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4610094428062439},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4485814869403839},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4384310841560364},{"id":"https://openalex.org/keywords/formal-methods","display_name":"Formal methods","score":0.42489200830459595},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.41537168622016907},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4101855754852295},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.29678040742874146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24233117699623108},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19565922021865845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1510341763496399},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13948127627372742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743329644203186},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6705431938171387},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.5817328691482544},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.5049083828926086},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4610094428062439},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4485814869403839},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4384310841560364},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.42489200830459595},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.41537168622016907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4101855754852295},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.29678040742874146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24233117699623108},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19565922021865845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1510341763496399},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13948127627372742},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v37i10.26407","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i10.26407","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26407/26179","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v37i10.26407","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i10.26407","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26407/26179","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1974542962","display_name":null,"funder_award_id":"Sk\u0142odowska","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2013768499","display_name":null,"funder_award_id":"665385","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2689612763","display_name":null,"funder_award_id":"Marie","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2913988464","display_name":"Vigilant Algorithmic Monitoring of Software","funder_award_id":"101020093","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7282925181","display_name":"Formal Methods for Stochastic Models: Algorithms and Applications","funder_award_id":"863818","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382318883.pdf"},"referenced_works_count":98,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W72346910","https://openalex.org/W431400460","https://openalex.org/W1496175338","https://openalex.org/W1506085041","https://openalex.org/W1518931405","https://openalex.org/W1530960252","https://openalex.org/W1673923490","https://openalex.org/W1845972764","https://openalex.org/W2033118636","https://openalex.org/W2049600235","https://openalex.org/W2077987282","https://openalex.org/W2084772009","https://openalex.org/W2107556430","https://openalex.org/W2110703708","https://openalex.org/W2133404041","https://openalex.org/W2155511972","https://openalex.org/W2164479831","https://openalex.org/W2293925890","https://openalex.org/W2462906003","https://openalex.org/W2548604229","https://openalex.org/W2736601468","https://openalex.org/W2740824349","https://openalex.org/W2784465508","https://openalex.org/W2793750335","https://openalex.org/W2803543472","https://openalex.org/W2885381174","https://openalex.org/W2892521964","https://openalex.org/W2898963688","https://openalex.org/W2925329277","https://openalex.org/W2936953762","https://openalex.org/W2937258472","https://openalex.org/W2949165985","https://openalex.org/W2962775887","https://openalex.org/W2963180405","https://openalex.org/W2963575966","https://openalex.org/W2968945909","https://openalex.org/W2970795963","https://openalex.org/W2971013032","https://openalex.org/W2972385330","https://openalex.org/W2981392333","https://openalex.org/W2982550324","https://openalex.org/W2995484204","https://openalex.org/W3006844914","https://openalex.org/W3024430860","https://openalex.org/W3035702124","https://openalex.org/W3037593164","https://openalex.org/W3046763300","https://openalex.org/W3091691175","https://openalex.org/W3107626576","https://openalex.org/W3107744858","https://openalex.org/W3119047266","https://openalex.org/W3120475579","https://openalex.org/W3123490258","https://openalex.org/W3145504837","https://openalex.org/W3173598197","https://openalex.org/W3178835226","https://openalex.org/W3186149862","https://openalex.org/W3186552360","https://openalex.org/W3207110310","https://openalex.org/W3212063444","https://openalex.org/W4226288564","https://openalex.org/W4230058301","https://openalex.org/W4281612951","https://openalex.org/W4281780103","https://openalex.org/W4283072363","https://openalex.org/W4283790991","https://openalex.org/W4286859462","https://openalex.org/W4287373626","https://openalex.org/W4289709949","https://openalex.org/W4293545785","https://openalex.org/W4294562617","https://openalex.org/W4298023569","https://openalex.org/W4301018745","https://openalex.org/W4306177474","https://openalex.org/W4312744983","https://openalex.org/W4382318213","https://openalex.org/W4382318883","https://openalex.org/W4394666657","https://openalex.org/W6602924617","https://openalex.org/W6629907426","https://openalex.org/W6635991797","https://openalex.org/W6637162671","https://openalex.org/W6677916085","https://openalex.org/W6684037837","https://openalex.org/W6718836005","https://openalex.org/W6737893269","https://openalex.org/W6743563064","https://openalex.org/W6747790125","https://openalex.org/W6764406268","https://openalex.org/W6767277667","https://openalex.org/W6779657896","https://openalex.org/W6780241948","https://openalex.org/W6785296287","https://openalex.org/W6789161987","https://openalex.org/W6798938860","https://openalex.org/W6799800074","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W2136512912","https://openalex.org/W2127267268","https://openalex.org/W2156446763","https://openalex.org/W2067910792","https://openalex.org/W2150194458","https://openalex.org/W2143461633","https://openalex.org/W2889071233","https://openalex.org/W4321471459","https://openalex.org/W4221156924","https://openalex.org/W2380814829"],"abstract_inverted_index":{"We":[0,158],"study":[1],"the":[2,20,45,72,155],"problem":[3],"of":[4,74,107,110],"learning":[5,55,167],"controllers":[6],"for":[7,23,113,139],"discrete-time":[8],"non-linear":[9,165],"stochastic":[10,105,164],"dynamical":[11],"systems":[12],"with":[13,36],"formal":[14,25,60],"reach-avoid":[15,26,76,137,156],"guarantees.":[16],"This":[17],"work":[18],"presents":[19],"first":[21],"method":[22,50],"providing":[24],"guarantees,":[27,35],"which":[28],"combine":[29],"and":[30,33,57,92],"generalize":[31],"stability":[32],"safety":[34],"a":[37,69,75,79,104,129,136,140,147],"tolerable":[38],"probability":[39],"threshold":[40],"p":[41],"in":[42,53,71,85],"[0,1]":[43],"over":[44],"infinite":[46],"time":[47],"horizon.":[48],"Our":[49,88,116],"leverages":[51],"advances":[52],"machine":[54],"literature":[56],"it":[58,123,151],"represents":[59],"certificates":[61],"as":[62,103],"neural":[63],"networks.":[64],"In":[65],"particular,":[66],"we":[67,83],"learn":[68,128],"certificate":[70],"form":[73],"supermartingale":[77],"(RASM),":[78],"novel":[80],"notion":[81],"that":[82],"introduce":[84],"this":[86],"work.":[87],"RASMs":[89],"provide":[90],"reachability":[91],"avoidance":[93],"guarantees":[94],"by":[95],"imposing":[96],"constraints":[97],"on":[98,162],"what":[99],"can":[100,124],"be":[101,125],"viewed":[102],"extension":[106],"level":[108],"sets":[109],"Lyapunov":[111],"functions":[112],"deterministic":[114],"systems.":[115],"approach":[117,161],"solves":[118],"several":[119],"important":[120],"problems":[121],"--":[122],"used":[126],"to":[127,134,145],"control":[130,142],"policy":[131,149],"from":[132],"scratch,":[133],"verify":[135],"specification":[138],"fixed":[141],"policy,":[143],"or":[144],"fine-tune":[146],"pre-trained":[148],"if":[150],"does":[152],"not":[153],"satisfy":[154],"specification.":[157],"validate":[159],"our":[160],"3":[163],"reinforcement":[166],"tasks.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}