7 citations · 9 across the 2 of their papers we have counts for
4 papers
Corruption-Robust Offline Reinforcement Learning
Xuezhou Zhang, Yiding Chen, Jerry Zhu +1
We study the adversarial robustness in offline reinforcement learning. Given a batch dataset consisting of tuples , an adversary is allowed to arbitrarily modify …
Robust Policy Gradient against Strong Data Corruption
Xuezhou Zhang, Yiding Chen, Xiaojin Zhu +1
We study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions. Our attack model assumes an \textit{adaptive} adversary who can…
Error Lower Bounds of Constant Step-size Stochastic Gradient Descent
Zhiyan Ding, Yiding Chen, Qin Li +1
Stochastic Gradient Descent (SGD) plays a central role in modern machine learning. While there is extensive work on providing error upper bound for SGD, not much is known about SGD…
Optimal Attack against Autoregressive Models by Manipulating the Environment
Yiding Chen, Xiaojin Zhu
We describe an optimal adversarial attack formulation against autoregressive time series forecast using Linear Quadratic Regulator (LQR). In this threat model, the environment evol…