default author photo

Anran Hu

University of California, Berkeley - Department of Industrial Engineering and Operations Research

4141 Etcheverry Hall

Berkeley, CA 94720-1777

United States

  • University of California, Berkeley - Department of Industrial Engineering and Operations Research

SCHOLARLY PAPERS

1

DOWNLOADS

118

TOTAL CITATIONS

11

Scholarly Papers (1)

Actions:
Email selected abstracts
1.

Logarithmic Regret for Episodic Continuous-Time Linear-Quadratic Reinforcement Learning Over a Finite-Time Horizon

Number of pages: 24 Posted: 23 May 2021
Matteo Basei, Xin Guo, Anran Hu and Yufei Zhang
EDF R&D, University of California, Berkeley - Department of Industrial Engineering and Operations Research, University of California, Berkeley - Department of Industrial Engineering and Operations Research and Imperial College London - Department of Mathematics
Downloads 118
Citation 11

Abstract:

Loading...

reinforcement learning, linear-quadratic, regret bound, continuous-time, time discretization