activity
20162023
most citedMultiplayer Reach-Avoid Games via Pairwise Outcomes

173 citations · 236 across the 22 of their papers we have counts for

collaborators

41 papers

cs.LG2023

Sample Complexity of Variance-reduced Distributionally Robust Q-learning

Shengbo Wang, Nian Si, Jose Blanchet +1

Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which th…

math.OC2023★ 2 cited

Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation

Zijian Liu, Zhengyuan Zhou

Recently, several studies consider the stochastic optimization problem but in a heavy-tailed noise regime, i.e., the difference between the stochastic gradient and the true gradien…

cs.LG2023★ 6 cited

A Finite Sample Complexity Bound for Distributionally Robust Q-learning

Shengbo Wang, Nian Si, Jose Blanchet +1

We consider a reinforcement learning setting in which the deployment environment is different from the training environment. Applying a robust Markov decision processes formulation…

cs.LG2023

Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise

Zijian Liu, Jiawei Zhang, Zhengyuan Zhou

We consider the stochastic optimization problem with smooth but not necessarily convex objectives in the heavy-tailed noise regime, where the stochastic gradient's noise is assumed…

cs.LG2023

Near-Optimal Non-Convex Stochastic Optimization under Generalized Smoothness

Zijian Liu, Srikanth Jagabathula, Zhengyuan Zhou

The generalized smooth condition, -smoothness, has triggered people's interest since it is more realistic in many optimization problems shown by both empirical and t…

stat.ML2023★ 1 cited

Single-Trajectory Distributionally Robust Reinforcement Learning

Zhipeng Liang, Xiaoteng Ma, Jose Blanchet +2

To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) ha…