{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:47:31Z","timestamp":1780332451921,"version":"3.54.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/cec55065.2022.9870209","type":"proceedings-article","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T19:28:14Z","timestamp":1662492494000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["Combining Soft-Actor Critic with Cross-Entropy Method for Policy Search in Continuous Control"],"prefix":"10.1109","author":[{"given":"Hieu Trung","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khang","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngoc Hoang","family":"Luong","sequence":"additional","affiliation":[{"name":"University of Information Technology,Ho Chi Minh City,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref13","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref14","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2017","journal-title":"ICLRE"},{"key":"ref15","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref17","article-title":"Soft Actor-Critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref18","author":"achiam","year":"2018","journal-title":"Spinning up in deep reinforcement learning"},{"key":"ref19","first-page":"25","author":"eiben","year":"2015","journal-title":"What Is an Evolutionary Algorithm?"},{"key":"ref4","author":"salimans","year":"2017","journal-title":"Evolution strategies as a scalable alternative to reinforcement learning"},{"key":"ref3","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"2019","journal-title":"ICLRE"},{"key":"ref6","article-title":"Guided evolutionary strategies: augmenting random search with surrogate gradients","author":"maheswaranathan","year":"2019","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2008.4631255"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref2","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"khadka","year":"2018","journal-title":"NeurIPS"},{"key":"ref9","article-title":"A closer look at deep policy gradients","author":"ilyas","year":"2020","journal-title":"ICLRE"},{"key":"ref1","article-title":"Review, analyze, and design a comprehensive deep reinforcement learning framework","volume":"abs 2002 11883","author":"nguyen","year":"2020","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref21","article-title":"Evolve to control: Evolution-based soft actor-critic for scalable reinforcement learning","volume":"abs 2007 13690","author":"suri","year":"2020","journal-title":"CoRR"},{"key":"ref24","article-title":"Tianshou: a highly modularized deep reinforcement learning library","author":"weng","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"OpenAI Gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref26","first-page":"10553","article-title":"Unbiased gradient estimation in unrolled computation graphs with persistent evolution strategies","author":"vicol","year":"2021","journal-title":"ICML 2021"},{"key":"ref25","first-page":"10299","article-title":"From complexity to simplicity: Adaptive es-active subspaces for blackbox optimization","author":"choromanski","year":"2019","journal-title":"NeurIPS"}],"event":{"name":"2022 IEEE Congress on Evolutionary Computation (CEC)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9870216\/9870201\/09870209.pdf?arnumber=9870209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T21:16:03Z","timestamp":1664226963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9870209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/cec55065.2022.9870209","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}