{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T04:41:04Z","timestamp":1759207264130},"reference-count":0,"publisher":"Sciedu Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIR"],"abstract":"<jats:p>Many studies have been done with the security of cloud computing. Though data encryption is a typical approach, high computing\u00a0complexity for encryption and decryption of data is needed. Therefore, safe system for distributed processing with secure data\u00a0attracts attention, and a lot of studies have been done. Secure multiparty computation (SMC) is one of these methods. Specifically,\u00a0two learning methods for machine learning (ML) with SMC are known. One is to divide learning data into several subsets and\u00a0perform learning. The other is to divide each item of learning data and perform learning. So far, most of works for ML with SMC\u00a0are ones with supervised and unsupervised learning such as BP and K-means methods. It seems that there does not exist any\u00a0studies for reinforcement learning (RL) with SMC. This paper proposes learning methods with SMC for Q-learning which is one\u00a0of typical methods for RL. The effectiveness of proposed methods is shown by numerical simulation for the maze problem.<\/jats:p>","DOI":"10.5430\/air.v6n2p57","type":"journal-article","created":{"date-parts":[[2017,5,24]],"date-time":"2017-05-24T01:15:59Z","timestamp":1495588559000},"page":"57","source":"Crossref","is-referenced-by-count":4,"title":["A proposal of privacy preserving reinforcement learning for secure multiparty computation"],"prefix":"10.5430","volume":"6","author":[{"given":"Hirofumi","family":"Miyajima","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noritaka","family":"Shigei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syunki","family":"Makino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiromi","family":"Miyajima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yohtaro","family":"Miyanishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Kitagami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norio","family":"Shiratori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3394","published-online":{"date-parts":[[2017,5,23]]},"container-title":["Artificial Intelligence Research"],"original-title":[],"link":[{"URL":"http:\/\/www.sciedu.ca\/journal\/index.php\/air\/article\/viewFile\/11280\/7117","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/www.sciedu.ca\/journal\/index.php\/air\/article\/viewFile\/11280\/7117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,5,24]],"date-time":"2017-05-24T01:16:00Z","timestamp":1495588560000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.sciedu.ca\/journal\/index.php\/air\/article\/view\/11280"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,23]]},"references-count":0,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2017,2,27]]}},"URL":"https:\/\/doi.org\/10.5430\/air.v6n2p57","relation":{},"ISSN":["1927-6982","1927-6974"],"issn-type":[{"value":"1927-6982","type":"electronic"},{"value":"1927-6974","type":"print"}],"subject":[],"published":{"date-parts":[[2017,5,23]]}}}