Sub-linear Regret in Adaptive Model Predictive Control

no code implementations • 7 Oct 2023 • Damianos Tranos, Alexandre Proutiere

Our result relies on a recently proposed exponential decay of sensitivity property and, to the best of our knowledge, is the first of its kind in this setting.

Model Predictive Control

Self-Tuning Tube-based Model Predictive Control

no code implementations • 2 Oct 2022 • Damianos Tranos, Alessio Russo, Alexandre Proutiere

We present Self-Tuning Tube-based Model Predictive Control (STT-MPC), an adaptive robust control algorithm for uncertain linear systems with additive disturbances based on the least-squares estimator and polytopic tubes.

Model Predictive Control

Regret Analysis in Deterministic Reinforcement Learning

no code implementations • 27 Jun 2021 • Damianos Tranos, Alexandre Proutiere

We consider Markov Decision Processes (MDPs) with deterministic transitions and study the problem of regret minimization, which is central to the analysis and design of optimal learning algorithms.

reinforcement-learning Reinforcement Learning (RL)

Exploration in Structured Reinforcement Learning

no code implementations • NeurIPS 2018 • Jungseul Ok, Alexandre Proutiere, Damianos Tranos

For Lipschitz MDPs, the bounds are shown not to scale with the sizes $S$ and $A$ of the state and action spaces, i. e., they are smaller than $c\log T$ where $T$ is the time horizon and the constant $c$ only depends on the Lipschitz structure, the span of the bias function, and the minimal action sub-optimality gap.

reinforcement-learning Reinforcement Learning (RL)