{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:40:07Z","timestamp":1770338407947,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"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":[[2021,3,3]]},"DOI":"10.1109\/csicc52343.2021.9420550","type":"proceedings-article","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T08:37:26Z","timestamp":1620463046000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Duplicated Replay Buffer for Asynchronous Deep Deterministic Policy Gradient"],"prefix":"10.1109","author":[{"given":"Seyed Mohammad","family":"Seyed Motehayeri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vahid","family":"Baghi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan Maani","family":"Miandoab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Moeini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"john","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref11","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":"ref12","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2015"},{"key":"ref13","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","author":"silver","year":"2014","journal-title":"Deterministic policy gradient algorithms"},{"key":"ref16","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref17","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018"},{"key":"ref18","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Shared experience actor-critic for multi-agent reinforcement learning","volume":"33","author":"christianos","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Combining deep reinforcement learning and safety based control for autonomous driving","author":"xiong","year":"2016"},{"key":"ref3","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017"},{"key":"ref6","article-title":"Asynchronous episodic deep deterministic policy gradient: Toward continuous control in computationally complex environments","author":"zhang","year":"2019","journal-title":"IEEE Transactions on Cybernetics"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref8","article-title":"Unity: A general platform for intelligent agents","author":"juliani","year":"2018"},{"key":"ref7","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref9","article-title":"The problem with ddpg: understanding failures in deterministic environments with sparse rewards","author":"matheron","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00039"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"}],"event":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","location":"Tehran, Iran","start":{"date-parts":[[2021,3,3]]},"end":{"date-parts":[[2021,3,4]]}},"container-title":["2021 26th International Computer Conference, Computer Society of Iran (CSICC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9420464\/9420539\/09420550.pdf?arnumber=9420550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:25Z","timestamp":1652197285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9420550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,3]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/csicc52343.2021.9420550","relation":{},"subject":[],"published":{"date-parts":[[2021,3,3]]}}}