LAUSR

Single trajectory-based policy optimization for discrete-time stochastic systems

Sign Up to like & get
recommendations!
0 Published in 2025 at "International Journal of General Systems"

DOI: 10.1080/03081079.2025.2474517

Abstract: Policy optimization has reemerged as an important approach for reinforcement learning and optimal control problems. A notable drawback is that even for linear quadratic problems, the execution of model-free policy optimization methods generally relies on… read more here.

Keywords: trajectory based; policy optimization; policy; single trajectory ... See more keywords

Single trajectory characterization via machine learning

Sign Up to like & get
recommendations!
0 Published in 2020 at "New Journal of Physics"

DOI: 10.1088/1367-2630/ab6065

Abstract: In order to study transport in complex environments, it is extremely important to determine the physical mechanism underlying diffusion, and precisely characterize its nature and parameters. Often, this task is strongly impacted by data consisting… read more here.

Keywords: single trajectory; characterization via; trajectory characterization; machine ... See more keywords

A Finite-Sample Bound for Identifying Partially Observed Linear Switched Systems From a Single Trajectory

Sign Up to like & get
recommendations!
0 Published in 2025 at "IEEE Control Systems Letters"

DOI: 10.1109/lcsys.2025.3580519

Abstract: We derive a finite-sample probabilistic bound on the parameter estimation error of a system identification algorithm for Linear Switched Systems. The algorithm estimates Markov parameters from a single trajectory and applies a variant of the… read more here.

Keywords: single trajectory; linear switched; sample bound; finite sample ... See more keywords