3 citations · 5 across the 12 of their papers we have counts for
17 papers
On the Effect of Instability on Learning Continuous-Time Linear Control Systems
Reza Sadeghi Hafshejani, Mohamad Kazem Shirani Fradonbeh
We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the poss…
Thompson Sampling in Partially Observable Contextual Bandits
Hongju Park, Mohamad Kazem Shirani Faradonbeh
Contextual bandits constitute a classical framework for decision-making under uncertainty. In this setting, the goal is to learn the arms of highest reward subject to contextual in…
Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes
Mohamad Kazem Shirani Faradonbeh, Sadegh Shirani, Mohsen Bayati
Linear diffusion processes serve as canonical continuous-time models for dynamic decision-making under uncertainty. These systems evolve according to drift matrices that specify th…
Regret Analysis of Certainty Equivalence Policies in Continuous-Time Linear-Quadratic Systems
Mohamad Kazem Shirani Faradonbeh
This work theoretically studies a ubiquitous reinforcement learning policy for controlling the canonical model of continuous-time stochastic linear-quadratic systems. We show that…
Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations
Hongju Park, Mohamad Kazem Shirani Faradonbeh
Contextual bandits are canonical models for sequential decision-making under uncertainty in environments with time-varying components. In this setting, the expected reward of each…
Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts
Hongju Park, Mohamad Kazem Shirani Faradonbeh
Contextual bandits are widely-used in the study of learning-based control policies for finite action spaces. While the problem is well-studied for bandits with perfectly observed c…