{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:23:03Z","timestamp":1762953783744,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,9,20]],"date-time":"2020-09-20T00:00:00Z","timestamp":1600560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,20]],"date-time":"2020-09-20T00:00:00Z","timestamp":1600560000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,20]],"date-time":"2020-09-20T00:00:00Z","timestamp":1600560000000},"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":[[2020,9,20]]},"DOI":"10.1109\/itsc45102.2020.9294300","type":"proceedings-article","created":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T23:14:55Z","timestamp":1608851695000},"page":"1-6","source":"Crossref","is-referenced-by-count":23,"title":["Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic"],"prefix":"10.1109","author":[{"given":"Yangang","family":"Ren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Risk-sensitive reinforcement learning: A constrained optimization viewpoint","author":"prashanth l","year":"2018","journal-title":"arXiv preprint arXiv 1810 09076"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9561","article-title":"Optimizing the cvar via sampling","author":"tamar","year":"2015","journal-title":"The AAAI Conference of Artificial Intelligence (AAAI)"},{"key":"ref12","first-page":"1437","article-title":"A comprehensive survey on safe rein-forcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Epopt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2016","journal-title":"arXiv preprint arXiv 1610 01283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref15","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning (ICML) JMLR org"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref17","article-title":"Distributional soft actor-critic: Off-policy reinforcement learning for addressing value estimation errors","author":"duan","year":"2020","journal-title":"arXiv preprint arXiv 2001 04786"},{"key":"ref18","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1801 01000"},{"key":"ref4","article-title":"As-sessing generalization in deep reinforcement learning","author":"packer","year":"2018","journal-title":"arXiv preprint arXiv 1810 10053"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref6","first-page":"1","article-title":"Sim-toreal transfer of robotic control with dynamics randomization","author":"peng","year":"2018","journal-title":"in 2018 IEEE International Conference on Robotics and Automation (ICRA) IEEE"},{"key":"ref5","article-title":"Investigating generalisation in continuous deep reinforcement learning","author":"zhao","year":"2019","journal-title":"arXiv preprint arXiv 1902 05023"},{"key":"ref8","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"pattanaik","year":"2018","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","start":{"date-parts":[[2020,9,20]]},"location":"Rhodes, Greece","end":{"date-parts":[[2020,9,23]]}},"container-title":["2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9294153\/9294168\/09294300.pdf?arnumber=9294300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T05:31:33Z","timestamp":1670563893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9294300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,20]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/itsc45102.2020.9294300","relation":{},"subject":[],"published":{"date-parts":[[2020,9,20]]}}}