SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics

20 April 2022

Papers citing "SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics"

4 / 4 papers shown

Title
On the Robustness of Safe Reinforcement Learning under Observational Perturbations Zuxin Liu Zijian Guo Zhepeng Cen Huan Zhang Jie Tan Bo-wen Li Ding Zhao OOD OffRL 37 35 0 29 May 2022
Towards Safe Reinforcement Learning with a Safety Editor Policy Haonan Yu Wei-ping Xu Haichao Zhang OffRL 61 31 0 28 Jan 2022
Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics Arsenii Kuznetsov Pavel Shvechikov Alexander Grishin Dmitry Vetrov 136 185 0 08 May 2020
Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach Yinlam Chow Aviv Tamar Shie Mannor Marco Pavone 64 310 0 06 Jun 2015