{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:15:28Z","timestamp":1766067328813,"version":"3.37.3"},"reference-count":22,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428174","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":3,"title":["Attentive Update of Multi-Critic for Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qing","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),CAS Key Laboratory of GIPAS, EEIS Department"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Ensemble adversarial training: Attacks and defenses","author":"tram\u00e8r","year":"2018","journal-title":"ICLRE"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0217-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015789"},{"key":"ref14","article-title":"An optimistic perspective on offline reinforcement learning","author":"agarwal","year":"2020","journal-title":"ICML"},{"key":"ref15","article-title":"Better exploration with optimistic actor critic","author":"ciosek","year":"2019","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref17","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref18","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref19","article-title":"Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2017","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref6","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"ICML"},{"key":"ref5","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2017","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"AAAI"},{"key":"ref7","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref9","article-title":"Sunrise: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","author":"lee","year":"2020","journal-title":"arXiv 2007 04938"},{"key":"ref20","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"ICLRE"},{"key":"ref22","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"ICLRE"},{"key":"ref21","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"ICLRE"}],"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\/09428174.pdf?arnumber=9428174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T13:57:50Z","timestamp":1672408670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428174","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}