{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:52:40Z","timestamp":1729673560884,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iccd46524.2019.00092","type":"proceedings-article","created":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T21:59:38Z","timestamp":1581371978000},"page":"638-647","source":"Crossref","is-referenced-by-count":5,"title":["Power Management of Wireless Sensor Nodes with Coordinated Distributed Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Shaswot","family":"Shresthamali","sequence":"first","affiliation":[]},{"given":"Masaaki","family":"Kondo","sequence":"additional","affiliation":[]},{"given":"Hiroshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24455-1_33"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422710"},{"key":"ref37","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"journal-title":"Japan Meteorological Agency","year":"2019","key":"ref35"},{"journal-title":"Tmote sky","year":"2019","key":"ref34"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref10"},{"key":"ref11","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref13","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015","journal-title":"arXiv preprint arXiv 1507 04296"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317927"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.03.056"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2018.00042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BEC.2018.8600992"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3302506.3310393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIOT.2018.00023"},{"key":"ref28","article-title":"Self-supervised exploration via disagreement","author":"pathak","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511405"},{"key":"ref27","article-title":"Deep attention recurrent q-network","author":"sorokin","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref3","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"arXiv preprint arXiv 1803 00933"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3293535"},{"key":"ref29","first-page":"1109","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.030413.121120"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SASO.2019.00015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2014.2316518"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3126495"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1274858.1274870"},{"journal-title":"E cient exploration in reinforcement learning","year":"1992","author":"thrun","key":"ref20"},{"key":"ref22","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv preprint arXiv 1703 10667"},{"key":"ref21","article-title":"Noisy networks for exploration","author":"fortunato","year":"2017","journal-title":"arXiv preprint arXiv 1706 10295"},{"key":"ref24","article-title":"Collaborative evolutionary reinforcement learning","author":"khadka","year":"2019","journal-title":"arXiv preprint arXiv 1905 00571"},{"key":"ref23","first-page":"1188","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"khadka","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref25","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"achiam","year":"2017","journal-title":"arXiv preprint arXiv 1703 01281"}],"event":{"name":"2019 IEEE 37th International Conference on Computer Design (ICCD)","start":{"date-parts":[[2019,11,17]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2019,11,20]]}},"container-title":["2019 IEEE 37th International Conference on Computer Design (ICCD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8970097\/8988587\/08988718.pdf?arnumber=8988718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T13:09:19Z","timestamp":1695733759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8988718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccd46524.2019.00092","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}