no code implementations • 7 Apr 2024 • Haitong Ma, Zhaolin Ren, Bo Dai, Na Li
Moreover, to handle the sim-to-real gap in the dynamics, we propose a skill discovery algorithm that learns new skills caused by the sim-to-real gap from real-world data.
no code implementations • 7 Mar 2024 • Zhaolin Ren, Na Li
This paper presents a new approach for batch Bayesian Optimization (BO) called Thompson Sampling-Regret to Sigma Ratio directed sampling (TS-RSR), where we sample a new batch of actions by minimizing a Thompson Sampling approximation of a regret to uncertainty ratio.
no code implementations • 8 Apr 2023 • Tongzheng Ren, Zhaolin Ren, Haitong Ma, Na Li, Bo Dai
This paper presents an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear stochastic systems.
no code implementations • 8 Sep 2022 • Aoxiao Zhong, Hao He, Zhaolin Ren, Na Li, Quanzheng Li
To make sure the FL model is robust when facing heterogeneous data among FL clients, most efforts focus on personalizing models for clients.
no code implementations • 1 Jun 2021 • Runyu Zhang, Zhaolin Ren, Na Li
We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting, and give a local convergence rate around strict NEs.
no code implementations • 3 Nov 2020 • Zhaolin Ren, Aoxiao Zhong, Na Li
In this work, we consider the general case where the target is allowed to be arbitrary, which we refer to as the LQR tracking problem.