{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T20:10:11Z","timestamp":1779221411452,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9304004","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T02:27:32Z","timestamp":1610504852000},"page":"572-577","source":"Crossref","is-referenced-by-count":8,"title":["Self-Guided Actor-Critic: Reinforcement Learning from Adaptive Expert Demonstrations"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenkun","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangtai","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Truncated horizon policy search: Combining reinforcement learning & imitation learning","author":"sun","year":"2018"},{"key":"ref11","first-page":"2469","article-title":"Policy Optimization with demonstrations","author":"kang","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref12","article-title":"Reinforcement learning from imperfect demonstrations under soft expert guidance","author":"jing","year":"2019"},{"key":"ref13","first-page":"1038","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989379"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref17","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-1354(98)00301-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3182\/20090712-4-TR-2008.00114"},{"key":"ref4","first-page":"1856","article-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"Equivalence between policy gradients and soft q-learning","author":"schulman","year":"2017"},{"key":"ref6","first-page":"3223","article-title":"Deep Q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref5","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017"},{"key":"ref8","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref2","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":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","article-title":"Reinforcement and imitation learning via interactive no-regret learning","author":"ross","year":"2014"},{"key":"ref20","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref22","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref21","first-page":"1582","article-title":"Addressing function Approximation error in actor-critic methods","author":"scott","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2016.04.018"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","location":"Jeju, Korea (South)","start":{"date-parts":[[2020,12,14]]},"end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09304004.pdf?arnumber=9304004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:48:17Z","timestamp":1779220097000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9304004\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9304004","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}