Implications Of Regret On Stability Of Linear Dynamical Systems

Abstract

The setting of an agent making decisions under uncertainty and under dynamic constraints is common for the fields of optimal control, reinforcement learning, and recently also for online learning. In the online learning setting, the quality of an agent's decision is often quantified by the concept of regret, comparing the performance of the chosen decisions to the best possible ones in hindsight. While regret is a useful performance measure, when dynamical systems are concerned, it is important to also assess the stability of the closed-loop system for a chosen policy. In this work, we show that for linear state feedback policies and linear systems subject to adversarial disturbances, linear regret implies asymptotic stability in both time-varying and time-invariant settings. Conversely, we also show that bounded input bounded state stability and summability of the state transition matrices imply linear regret.

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keykarapetyan2022implications

Related papers

• Logarithmic Regret For Nonlinear Control (2025)0.00
• Foundations Of Safe Online Reinforcement Learning In The Linear Quadratic Regulator: \(\sqrt{t}\)-regret (2025)0.00
• Regret Bounds For Decentralized Learning In Cooperative Multi-agent Dynamical Systems (2020)0.00
• First-order Regret In Reinforcement Learning With Linear Function Approximation: A Robust Estimation Approach (2021)0.00
• Online Learning With Dynamics: A Minimax Perspective (2020)0.00
• Dynamic Regret Of Online Markov Decision Processes (2022)0.00
• Towards Optimal Regret In Adversarial Linear Mdps With Bandit Feedback (2023)0.00
• Reinforcement Learning With Fast Stabilization In Linear Dynamical Systems (2020)0.00