{"id":"https://openalex.org/W3164250586","doi":"https://doi.org/10.1109/coins51742.2021.9524260","title":"RL-IoT: Reinforcement Learning to Interact with IoT Devices","display_name":"RL-IoT: Reinforcement Learning to Interact with IoT Devices","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3164250586","doi":"https://doi.org/10.1109/coins51742.2021.9524260","mag":"3164250586"},"language":"en","primary_location":{"id":"doi:10.1109/coins51742.2021.9524260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coins51742.2021.9524260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.00884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043645178","display_name":"Giulia Milan","orcid":"https://orcid.org/0000-0002-5540-2264"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giulia Milan","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy","Politecnico di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064639744","display_name":"Luca Vassio","orcid":"https://orcid.org/0000-0002-2920-1856"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Vassio","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy","Politecnico di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077745494","display_name":"Id\u00edlio Drago","orcid":"https://orcid.org/0000-0003-1932-1261"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Idilio Drago","raw_affiliation_strings":["University of Turin,Turin,Italy","University of Turin, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"University of Turin,Turin,Italy","institution_ids":["https://openalex.org/I55143463"]},{"raw_affiliation_string":"University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060087704","display_name":"Marco Mellia","orcid":"https://orcid.org/0000-0003-1859-6693"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Mellia","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy","Politecnico di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043645178"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68323231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9919000267982483,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8366835117340088},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7810957431793213},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.7132909893989563},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.6722808480262756},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6622164845466614},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.544246256351471},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5434744954109192},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4396122694015503},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4117131531238556},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3845764398574829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34328025579452515},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3349866271018982},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2637573480606079},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.20020699501037598},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14577391743659973},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07616141438484192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366835117340088},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7810957431793213},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.7132909893989563},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.6722808480262756},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6622164845466614},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.544246256351471},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5434744954109192},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4396122694015503},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4117131531238556},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3845764398574829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34328025579452515},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3349866271018982},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2637573480606079},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20020699501037598},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14577391743659973},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07616141438484192},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/coins51742.2021.9524260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coins51742.2021.9524260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.00884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00884","pdf_url":"https://arxiv.org/pdf/2105.00884","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.00884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.00884","pdf_url":"https://arxiv.org/pdf/2105.00884","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W179510128","https://openalex.org/W755046805","https://openalex.org/W2049867480","https://openalex.org/W2082135129","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2288490641","https://openalex.org/W2581042172","https://openalex.org/W2886190986","https://openalex.org/W2946123090","https://openalex.org/W2954035548","https://openalex.org/W3092021803","https://openalex.org/W3104487880","https://openalex.org/W3164250586","https://openalex.org/W4251550354","https://openalex.org/W6607214813"],"related_works":["https://openalex.org/W2093262417","https://openalex.org/W2123131699","https://openalex.org/W650116260","https://openalex.org/W2378329187","https://openalex.org/W4390790060","https://openalex.org/W2134191509","https://openalex.org/W3209454962","https://openalex.org/W79697243","https://openalex.org/W2314257840","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Our":[0,133],"life":[1],"is":[2,37,138],"getting":[3],"filled":[4],"by":[5],"Internet":[6],"of":[7,45,76,83,95,104],"Things":[8],"(IoT)":[9],"devices.":[10,66],"These":[11],"devices":[12,32],"often":[13],"rely":[14],"on":[15],"closed":[16],"or":[17],"poorly":[18,186],"documented":[19,187],"protocols,":[20,189],"with":[21,30,62,117,157,172,185],"unknown":[22,64],"formats":[23],"and":[24,42,79,144],"semantics.":[25],"Learning":[26],"how":[27,58,153],"to":[28,59,72,80,86,99,128,140,154],"interact":[29,61],"such":[31],"in":[33,165],"an":[34],"autonomous":[35],"manner":[36],"the":[38,74,84,93,118,130,158,180],"key":[39],"for":[40,182],"interoperability":[41],"automatic":[43,183],"verification":[44],"their":[46],"capabilities.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"RL-IoT,":[53],"a":[54,88,102,161],"system":[55],"that":[56,125,136],"explores":[57],"automatically":[60],"possibly":[63],"IoT":[65,106,120,188],"We":[67,97],"leverage":[68],"reinforcement":[69],"learning":[70,122],"(RL)":[71],"recover":[73],"semantics":[75,110],"protocol":[77,107],"messages":[78,116],"take":[81],"control":[82],"device":[85],"reach":[87,129],"given":[89,131],"goal,":[90],"while":[91],"minimizing":[92],"number":[94],"interactions.":[96,177],"assume":[98],"know":[100],"only":[101],"database":[103],"possible":[105],"messages,":[108],"whose":[109],"are":[111,126],"however":[112],"unknown.":[113],"RL-IoT":[114,137,151,178],"exchanges":[115],"target":[119,159],"device,":[121,160],"those":[123],"commands":[124],"useful":[127],"goal.":[132],"results":[134],"show":[135],"able":[139],"solve":[141],"both":[142],"simple":[143],"complex":[145],"tasks.":[146],"With":[147],"properly":[148],"tuned":[149],"parameters,":[150],"learns":[152],"perform":[155],"actions":[156],"Yeelight":[162],"smart":[163],"bulb":[164],"our":[166],"case":[167],"study,":[168],"completing":[169],"non-trivial":[170],"patterns":[171],"as":[173,175],"few":[174],"400":[176],"paves":[179],"road":[181],"interactions":[184],"thus":[190],"enabling":[191],"interoperable":[192],"systems.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
