{"authors":[{"id":null,"fullName":"Balazadeh, Vahid","name":"Vahid","surname":"Balazadeh","rank":1,"pid":null},{"id":null,"fullName":"De, Abir","name":null,"surname":null,"rank":2,"pid":null},{"id":null,"fullName":"Singla, Adish","name":"Adish","surname":"Singla","rank":3,"pid":null},{"id":null,"fullName":"Gomez-Rodriguez, Manuel","name":"Manuel","surname":"Gomez-Rodriguez","rank":4,"pid":null}],"openAccessColor":null,"publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":null,"subjects":[{"subject":{"scheme":"FOS","value":"0301 basic medicine"},"provenance":null},{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Human-Computer Interaction"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (stat.ML)"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Systems and Control (eess.SY)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Electrical Engineering and Systems Science - Systems and Control"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Human-Computer Interaction (cs.HC)"},"provenance":null},{"subject":{"scheme":"FOS","value":"03 medical and health sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Computers and Society"},"provenance":null},{"subject":{"scheme":"keyword","value":"Statistics - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computers and Society (cs.CY)"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"FOS: Electrical engineering, electronic engineering, information engineering"},"provenance":null}],"mainTitle":"Learning to Switch Among Agents in a Team via 2-Layer Markov Decision Processes","subTitle":null,"descriptions":["Reinforcement learning agents have been mostly developed and evaluated under the assumption that they will operate in a fully autonomous manner -- they will take all actions. In this work, our goal is to develop algorithms that, by learning to switch control between agents, allow existing reinforcement learning agents to operate under different automation levels. To this end, we first formally define the problem of learning to switch control among agents in a team via a 2-layer Markov decision process. Then, we develop an online learning algorithm that uses upper confidence bounds on the agents' policies and the environment's transition probabilities to find a sequence of switching policies. The total regret of our algorithm with respect to the optimal switching policy is sublinear in the number of learning steps and, whenever multiple teams of agents operate in a similar environment, our algorithm greatly benefits from maintaining shared confidence bounds for the environments' transition probabilities and it enjoys a better regret bound than problem-agnostic algorithms. Simulation experiments in an obstacle avoidance task illustrate our theoretical findings and demonstrate that, by exploiting the specific structure of the problem, our proposed algorithm is superior to problem-agnostic algorithms.","Published in Transactions on Machine Learning Research"],"publicationDate":"2020-01-01","publisher":null,"embargoEndDate":"2020-02-01","sources":["Transactions on Machine Learning Research"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Transactions on Machine Learning Research","issnPrinted":"2835-8856","issnOnline":null,"issnLinking":null,"ep":null,"iss":null,"sp":null,"vol":null,"edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::38e4c2930ec03e39d0db8ddbd154c1fe","originalIds":["50|datacite____::38e4c2930ec03e39d0db8ddbd154c1fe","10.48550/arxiv.2002.04258","50|od________18::b4a308481cc5820292a63b92e8da5fc7","oai:arXiv.org:2002.04258","50|r3c4b2081b22::38e4c2930ec03e39d0db8ddbd154c1fe"],"pids":[{"scheme":"doi","value":"10.48550/arxiv.2002.04258"},{"scheme":"arXiv","value":"2002.04258"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":0.0,"influence":2.1746283E-9,"popularity":1.1111055E-9,"impulse":0.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C5"}},"projects":[{"id":"corda__h2020::83d6aa753c4b6e94582f4ef733616892","code":"945719","acronym":"HumanML","title":"Human-Centric Machine Learning","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/945719"}]}],"organizations":[{"legalName":"Max Planck Society","acronym":"MPG","id":"openorgs____::5a405a89387d1881afa956f475994e10","pids":[{"scheme":"ISNI","value":"0000000121051091"},{"scheme":"ROR","value":"https://ror.org/01hhn8329"},{"scheme":"GRID","value":"grid.4372.2"},{"scheme":"PIC","value":"999990267"},{"scheme":"RRID","value":"RRID:nlx_55250"},{"scheme":"FundRef","value":"501100004189"},{"scheme":"RRID","value":"RRID:SCR_011366"},{"scheme":"Wikidata","value":"Q158085"},{"scheme":"OrgRef","value":"614753"},{"scheme":"mag_id","value":"149899117"},{"scheme":"wikidata","value":"Q158085"},{"scheme":"fundref","value":"501100004189"}],"countries":[{"code":"DE","label":"Germany"}],"websiteurl":"http://www.mpg.de/en"},{"legalName":"Sharif University of Technology","acronym":"SUT","id":"openorgs____::ec543340be254f436c7e6019c4db0a07","pids":[{"scheme":"FundRef","value":"501100002398"},{"scheme":"FundRef","value":"501100006723"},{"scheme":"GRID","value":"grid.412553.4"},{"scheme":"fundref","value":"501100006674"},{"scheme":"ROR","value":"https://ror.org/024c2fq17"},{"scheme":"Wikidata","value":"Q2096604"},{"scheme":"ISNI","value":"0000000107409747"},{"scheme":"wikidata","value":"Q2096604"},{"scheme":"fundref","value":"501100006723"},{"scheme":"OrgRef","value":"453155"},{"scheme":"fundref","value":"501100002398"},{"scheme":"mag_id","value":"133529467"},{"scheme":"FundRef","value":"501100006674"}],"countries":[{"code":"IR","label":"Iran (Islamic Republic of)"}],"websiteurl":"http://www.sharif.ir/web/en"},{"legalName":"Sharif University of Technology (Sharif Policy Research Institute)","acronym":"Sharif University of Technology (Sharif Policy Research Institute)","id":"pending_org_::d445a5f8db66041b233faa66cfe3516d","pids":null,"countries":[{"code":"IR","label":"Iran (Islamic Republic of)"}],"websiteurl":null}],"communities":null,"collectedFrom":[{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"},{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},{"key":"re3data_____::c4b2081b224be6b3e79d0e5e5556f631","value":"European Union Open Data Portal"}],"instances":[{"pids":[{"scheme":"doi","value":"10.48550/arxiv.2002.04258"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.2002.04258"],"publicationDate":"2020-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"}},{"pids":[{"scheme":"arXiv","value":"2002.04258"}],"accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Preprint","urls":["http://arxiv.org/abs/2002.04258"],"publicationDate":"2020-02-11","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},"collectedFrom":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.48550/arxiv.2002.04258"}],"type":"Article","urls":["http://dx.doi.org/10.48550/arxiv.2002.04258"],"publicationDate":"2022-01-01","refereed":"peerReviewed","hostedBy":{"key":"doajarticles::fff7f51da804d5ea5ea854438e205281","value":"Transactions on Machine Learning Research"},"collectedFrom":{"key":"re3data_____::c4b2081b224be6b3e79d0e5e5556f631","value":"European Union Open Data Portal"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda__h2020::83d6aa753c4b6e94582f4ef733616892","relatedRecordType":"project","relationProvenance":"sysimport:crosswalk","trust":"0.9"},"collectedfrom":[{"dsId":"openaire____::a55eb91348674d853191f4f4fd73d078","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon 2020"}],"projectTitle":"Human-Centric Machine Learning","code":"945719","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::H2020","description":"Horizon 2020 Framework Programme","name":"H2020"},"level1":{"id":"ec__________::EC::H2020::ERC","description":"European Research Council","name":"ERC"},"level2":{"id":"ec__________::EC::H2020::ERC::ERC-STG","description":"Starting Grant","name":"ERC-STG"}},"startDate":"2020-11-01","endDate":"2025-10-31"}],"otherTitles":null,"green":true,"inDiamondJournal":false,"isGreen":true,"isInDiamondJournal":false}