{"id":"https://openalex.org/W4282960160","doi":"https://doi.org/10.3390/s22124491","title":"Learning Dynamics and Control of a Stochastic System under Limited Sensing Capabilities","display_name":"Learning Dynamics and Control of a Stochastic System under Limited Sensing Capabilities","publication_year":2022,"publication_date":"2022-06-14","ids":{"openalex":"https://openalex.org/W4282960160","doi":"https://doi.org/10.3390/s22124491","pmid":"https://pubmed.ncbi.nlm.nih.gov/35746272"},"language":"en","primary_location":{"id":"doi:10.3390/s22124491","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22124491","pdf_url":"https://www.mdpi.com/1424-8220/22/12/4491/pdf?version=1655198080","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/12/4491/pdf?version=1655198080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085905666","display_name":"Mohammad Amin Zadenoori","orcid":"https://orcid.org/0000-0003-4591-153X"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Mohammad Amin Zadenoori","raw_affiliation_strings":["Department of Information Engineering, University of Florence, 50139 Firenze, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4591-153X","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Florence, 50139 Firenze, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037029993","display_name":"Enrico Vicario","orcid":"https://orcid.org/0000-0002-4983-4386"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico Vicario","raw_affiliation_strings":["Department of Information Engineering, University of Florence, 50139 Firenze, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4983-4386","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Florence, 50139 Firenze, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085905666"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04862846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"12","first_page":"4491","last_page":"4491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9902999997138977,"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"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9902999997138977,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9796000123023987,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9706000089645386,"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":0.6574821472167969},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5525760054588318},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.5467100143432617},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.517377495765686},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5126132369041443},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.46390172839164734},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.44209519028663635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44168171286582947},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.43835288286209106},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4314559996128082},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42786169052124023},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40814337134361267},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.40166351199150085},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.37907105684280396},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3517506718635559},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3464776277542114},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.34524989128112793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3302220404148102},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.32779985666275024},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.24481692910194397},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2244795262813568},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20247289538383484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13423803448677063},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11180531978607178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6574821472167969},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5525760054588318},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.5467100143432617},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.517377495765686},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5126132369041443},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.46390172839164734},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.44209519028663635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44168171286582947},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.43835288286209106},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4314559996128082},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42786169052124023},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40814337134361267},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.40166351199150085},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37907105684280396},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3517506718635559},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3464776277542114},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.34524989128112793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3302220404148102},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.32779985666275024},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24481692910194397},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2244795262813568},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20247289538383484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13423803448677063},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11180531978607178},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.3390/s22124491","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22124491","pdf_url":"https://www.mdpi.com/1424-8220/22/12/4491/pdf?version=1655198080","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:35746272","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35746272","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:b5771fc0af6c414d89e9bd28bc6741a2","is_oa":true,"landing_page_url":"https://doaj.org/article/b5771fc0af6c414d89e9bd28bc6741a2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 22, Iss 12, p 4491 (2022)","raw_type":"article"},{"id":"pmh:oai:flore.unifi.it:2158/1289945","is_oa":false,"landing_page_url":"https://hdl.handle.net/2158/1289945","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/12/4491/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22124491","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 22; Issue 12; Pages: 4491","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9230096","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9230096","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22124491","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22124491","pdf_url":"https://www.mdpi.com/1424-8220/22/12/4491/pdf?version=1655198080","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4282960160.pdf","grobid_xml":"https://content.openalex.org/works/W4282960160.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1532688806","https://openalex.org/W1974191989","https://openalex.org/W2034725503","https://openalex.org/W2043711897","https://openalex.org/W2044375425","https://openalex.org/W2051090942","https://openalex.org/W2081808304","https://openalex.org/W2083443252","https://openalex.org/W2099667085","https://openalex.org/W2117109565","https://openalex.org/W2125838338","https://openalex.org/W2126191527","https://openalex.org/W2153700957","https://openalex.org/W2165959773","https://openalex.org/W2168359464","https://openalex.org/W2169209873","https://openalex.org/W2169778923","https://openalex.org/W2170510068","https://openalex.org/W2177271944","https://openalex.org/W2207662037","https://openalex.org/W2251007294","https://openalex.org/W2273088453","https://openalex.org/W2359042397","https://openalex.org/W2480680997","https://openalex.org/W2501353069","https://openalex.org/W2506987745","https://openalex.org/W2601424933","https://openalex.org/W2777834579","https://openalex.org/W2798609170","https://openalex.org/W2896505283","https://openalex.org/W2914494945","https://openalex.org/W2945844330","https://openalex.org/W2994844380","https://openalex.org/W2998415999","https://openalex.org/W3035965352","https://openalex.org/W3099878876","https://openalex.org/W3119087294","https://openalex.org/W3169607806","https://openalex.org/W3192182354","https://openalex.org/W3211437098","https://openalex.org/W6632300202","https://openalex.org/W6677916933","https://openalex.org/W6686103050"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W4321379664"],"abstract_inverted_index":{"The":[0,187,312,328],"operation":[1],"of":[2,5,18,24,61,70,83,90,96,99,123,126,132,143,172,178,204,206,211,256,265,320,330],"a":[3,16,103,111,173,179,318,324],"variety":[4],"natural":[6],"or":[7],"man-made":[8],"systems":[9],"subject":[10],"to":[11,33,154,239,303,304,309],"uncertainty":[12],"is":[13,39,75,190,268,315,334],"maintained":[14],"within":[15],"range":[17],"safe":[19],"behavior":[20],"through":[21],"run-time":[22],"sensing":[23,82],"the":[25,37,45,62,67,71,81,84,94,124,133,140,163,169,176,185,195,201,212,219,226,241,250,257,262,266,281,286,297,306,331,338,342,348],"system":[26,38,72,85,105,134,213,216,243],"state":[27,86,135,170,255,263],"and":[28,52,66,87,129,215,245,271,345],"control":[29,46,64,100,127],"actions":[30,65,101,128,248],"selected":[31],"according":[32],"some":[34,144],"strategy.":[35],"When":[36],"observed":[40],"from":[41,184],"an":[42,152,156],"external":[43],"perspective,":[44],"strategy":[47],"may":[48,288],"not":[49,289],"be":[50,56,290],"known":[51],"it":[53],"should":[54],"rather":[55],"reconstructed":[57],"by":[58,78,139,175,192,336],"joint":[59],"observation":[60],"applied":[63,207],"corresponding":[68],"evolution":[69],"state.":[73],"This":[74],"largely":[76],"hurdled":[77,191],"limitations":[79],"in":[80,249,260,317],"different":[88],"levels":[89],"noise.":[91],"We":[92],"address":[93],"problem":[95],"optimal":[97],"selection":[98],"for":[102,116,293,323],"stochastic":[104,165,233],"with":[106,113,225],"unknown":[107,114],"dynamics":[108,171,244,264],"operating":[109],"under":[110],"controller":[112],"strategy,":[115],"which":[117,136,261],"we":[118,150,301],"can":[119],"observe":[120],"trajectories":[121,205],"made":[122],"sequence":[125],"noisy":[130,209],"observations":[131,210],"are":[137,200,274],"labeled":[138],"exact":[141],"value":[142],"reward":[145,340],"functions.":[146],"To":[147],"this":[148],"end,":[149],"present":[151],"approach":[153],"train":[155],"Input-Output":[157],"Hidden":[158],"Markov":[159],"Model":[160],"(IO-HMM)":[161],"as":[162],"generative":[164,234],"model":[166,282,310],"that":[167,283],"describes":[168],"POMDP":[174,267],"application":[177],"novel":[180],"optimization":[181,299],"objective":[182],"adopted":[183],"literate.":[186],"learning":[188],"task":[189],"two":[193],"restrictions:":[194],"only":[196],"available":[197],"sensed":[198],"data":[199,287,344],"limited":[202],"number":[203],"actions,":[208],"state,":[214],"state;":[217],"and,":[218],"high":[220],"failure":[221,321],"costs":[222],"prevent":[223],"interaction":[224],"online":[227],"environment,":[228],"preventing":[229],"exploratory":[230],"testing.":[231],"Traditionally,":[232],"models":[235],"have":[236],"been":[237],"used":[238],"learn":[240],"underlying":[242],"select":[246],"appropriate":[247],"defined":[251],"task.":[252],"However,":[253],"current":[254],"art":[258],"techniques,":[259],"first":[269],"learned":[270],"then":[272],"strategies":[273],"optimized":[275],"over":[276],"it,":[277],"frequently":[278],"fail":[279],"because":[280],"best":[284],"fits":[285],"well":[291],"suited":[292],"controlling.":[294],"By":[295],"using":[296,337],"aforementioned":[298],"objective,":[300],"try":[302],"tackle":[305],"problems":[307],"related":[308],"mis-specification.":[311],"proposed":[313],"methodology":[314],"illustrated":[316],"scenario":[319],"avoidance":[322],"multi":[325],"component":[326],"system.":[327],"quality":[329],"decision":[332],"making":[333],"evaluated":[335],"collected":[339],"on":[341],"test":[343],"compared":[346],"against":[347],"previous":[349],"literature":[350],"usual":[351],"approach.":[352]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}