{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T01:02:31Z","timestamp":1730250151357,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"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":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428188","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Ddper: Decentralized Distributed Prioritized Experience Replay"],"prefix":"10.1109","author":[{"given":"Sidun","family":"Liu","sequence":"first","affiliation":[{"name":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Qiao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Dou","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongchun","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Seed rl: Scalable and efficient deep-rl with accelerated central inference","year":"2019","author":"espeholt","key":"ref10"},{"article-title":"Massively parallel methods for deep reinforcement learning","year":"2015","author":"nair","key":"ref11"},{"key":"ref12","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"ICML"},{"key":"ref13","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"NeurIPS"},{"article-title":"Deep reinforcement learning with double q-learning","year":"2015","author":"van hasselt","key":"ref14"},{"key":"ref15","article-title":"Recurrent experience replay in distributed reinforcement learning","author":"kapturowski","year":"2018","journal-title":"ICLRE"},{"article-title":"Observe and look further: Achieving consistent performance on atari","year":"2018","author":"pohlen","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Never give up: Learning directed exploration strategies","year":"2020","author":"puigdom\u00e8nech badia","key":"ref18"},{"key":"ref19","first-page":"507","article-title":"Agent57: Outperforming the atari human benchmark","author":"puigdom\u00e8nech badia","year":"2020","journal-title":"Int Conference on Machine Learning"},{"article-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref4"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"article-title":"Distributed prioritized experience replay","year":"2018","author":"horgan","key":"ref5"},{"key":"ref8","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"NeurIPS"},{"key":"ref7","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref2"},{"article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","year":"2018","author":"espeholt","key":"ref9"},{"key":"ref1","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":"Deep q-learning from demonstrations","year":"2017","author":"hester","key":"ref20"},{"article-title":"Rainbow: Combining improvements in deep reinforcement learning","year":"2017","author":"hessel","key":"ref21"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428188.pdf?arnumber=9428188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T21:27:47Z","timestamp":1656365267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428188","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}