Policy gradient method for LQG control via input–output-history representation: Convergence to O ( ϵ ) -stationary points

Systems & Control Letters 2026

View at publisher

Authors: Tomonori Sadamoto, Takashi Tanaka

DOI: 10.1016/j.sysconle.2025.106289

Cited by: 0

References: 15

Fields of Study & Subjects

Adaptive Dynamic Programming Control Reinforcement Learning in Robotics Advanced Control Systems Optimization

References 15