{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:20:33Z","timestamp":1740100833897,"version":"3.37.3"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T00:00:00Z","timestamp":1656979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T00:00:00Z","timestamp":1656979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,5]]},"DOI":"10.1109\/icufn55119.2022.9829571","type":"proceedings-article","created":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T19:37:36Z","timestamp":1658345856000},"page":"320-325","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Correctness of Reinforcement Learning based on Actor-Critic Algorithm"],"prefix":"10.1109","author":[{"given":"Youngjae","family":"Kim","sequence":"first","affiliation":[{"name":"Chungbuk National University,College of Electrical & Computer Engineering,Cheongju,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manzoor","family":"Hussain","sequence":"additional","affiliation":[{"name":"Chungbuk National University,College of Electrical & Computer Engineering,Cheongju,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae-Won","family":"Suh","sequence":"additional","affiliation":[{"name":"Chungbuk National University,College of Electrical & Computer Engineering,Cheongju,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jang-Eui","family":"Hong","sequence":"additional","affiliation":[{"name":"Chungbuk National University,College of Electrical & Computer Engineering,Cheongju,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref11","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref12","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref13","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","author":"kuznetsov","year":"2020","journal-title":"Proceedings of 7th International Conference on Machine Learning"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref14"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/1541931218621047"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DISA.2018.8490530"},{"article-title":"Reinforcement learning: An introduction","year":"2018","author":"sutton","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58793-2_2"},{"article-title":"Actor-critic algorithms - Advances in neural information processing systems","year":"1999","author":"konda","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194020400227"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref9"}],"event":{"name":"2022 Thirteenth International Conference on Ubiquitous and Future Networks (ICUFN)","start":{"date-parts":[[2022,7,5]]},"location":"Barcelona, Spain","end":{"date-parts":[[2022,7,8]]}},"container-title":["2022 Thirteenth International Conference on Ubiquitous and Future Networks (ICUFN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9829530\/9829531\/09829571.pdf?arnumber=9829571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T20:01:04Z","timestamp":1659988864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9829571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,5]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icufn55119.2022.9829571","relation":{},"subject":[],"published":{"date-parts":[[2022,7,5]]}}}