Akshay Mete

2 accepted papers

2024

Finite Time Logarithmic Regret Bounds for Self-Tuning Regulation

Rahul Singh, Akshay Mete, Avik Kar, Panganamala Kumar

ICML 2024poster

We establish the first finite-time logarithmic regret bounds for the self-tuning regulation problem. We introduce a modified version of the certainty equivalence algorithm, which we call PIECE, that clips inputs in addition to utilizing probing inputs for exploration. We show that it has a $C \log T…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems

Akshay Mete, Rahul Singh, Panganamala Kumar

NeurIPS 2022accept

We consider the problem of controlling an unknown stochastic linear system with quadratic costs -- called the adaptive LQ control problem. We re-examine an approach called ``Reward-Biased Maximum Likelihood Estimate'' (RBMLE) that was proposed more than forty years ago, and which predates the ``Uppe…

Cited by 13 Source ↗PDF ↗Scholar ↗