Problem
Research questions and friction points this paper is trying to address.
Distributed Online Optimization
Multi-Agent Systems
Dynamic Regret
Input Constraints
Time-Varying Cost Functions
Projection-Free Bandit Online Optimization for Multi-Agent Systems with Dynamic Regret
🤖 AI Summary
本文针对多智能体系统的在线优化问题，提出了一种无需准确系统模型、基于实时输入输出数据的无投影带反馈优化算法，并证明了其有效性。
📝 Abstract
This paper investigates distributed online optimization for multi-agent dynamical systems with constrained inputs and time-varying cost functions. While online convex optimization offers a principal framework for sequential decision-making, existing online learning and optimization algorithms typically require accurate system models, limiting their applicability in practical settings. To overcome this challenge, we propose a distributed bandit online feedback optimization algorithm that relies solely on real-time input-output data. The algorithm employs a smoothing zeroth-order one-point estimator to construct local gradient approximations directly from cost evaluations. Additionally, to enforce input constraints effectively, we integrate a projection-free conditional gradient update, making the algorithm well-suited for online and large-scale settings. Furthermore, we establish a sublinear dynamic regret bound that depends on a temporal variation measure of system non-stationarity. Finally, numerical simulations demonstrate the effectiveness of the proposed algorithm.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Distributed Bandit Online Feedback Optimization
Projection-Free Conditional Gradient Update
Smoothing Zeroth-Order One-Point Estimator
Dynamic Regret Bound
🔎 Similar Papers
No similar papers found.
