{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:10:17Z","timestamp":1767337817302,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1109\/smc52423.2021.9658890","type":"proceedings-article","created":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:34:35Z","timestamp":1641501275000},"page":"2170-2176","source":"Crossref","is-referenced-by-count":1,"title":["Shared Trained Models Selection and Management for Transfer Reinforcement Learning in Open IoT"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Noguchi","sequence":"first","affiliation":[{"name":"Nippon Telegraph and Telephone Corporation,NTT Network Innovation Center,Tokyo,Japan,180-8585"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuma","family":"Isoda","sequence":"additional","affiliation":[{"name":"NTT DOCOMO,R&D Innovation Division,Kanagawa,Japan,239-8536"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seisuke","family":"Arai","sequence":"additional","affiliation":[{"name":"Nippon Telegraph and Telephone Corporation,NTT Network Innovation Center,Tokyo,Japan,180-8585"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","year":"2018","author":"kalashnikov","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"article-title":"Model-Agnostic Meta-Learning for fast adaptation of deep networks","year":"2017","author":"chelsea","key":"ref13"},{"key":"ref14","first-page":"2396","article-title":"Meta-gradient reinforcement learning","volume":"31","author":"xu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"323","article-title":"NoRML: No-reward meta learning","author":"yang","year":"2019","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref16","first-page":"4496","article-title":"Distral: robust multitask reinforcement learning","volume":"30","author":"teh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"1087","article-title":"One-shot imitation learning 30","author":"duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref19","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc 31st AAAI Conference on Artificial Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-016-0528-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP-W.2014.7046678"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.941632"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2019.2950719"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","first-page":"2503","article-title":"Hidden technical debt in machine learning systems","volume":"28","author":"sculley","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"The internet of things: Mapping the value beyond the hype","author":"manyika","year":"2015","journal-title":"Technical Report"},{"journal-title":"Cisco Annual Internet Report (2018–2023) White Paper","year":"2020","key":"ref1"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"article-title":"Stochastic neural networks for hierarchical reinforcement learning","year":"2017","author":"florensa","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc International Conference on Machine Learning"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2368997"}],"event":{"name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2021,10,17]]},"location":"Melbourne, Australia","end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9658572\/9658575\/09658890.pdf?arnumber=9658890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:33:09Z","timestamp":1655760789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9658890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/smc52423.2021.9658890","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}