Poster

A Regret Minimization Approach to Multi-Agent Control

Udaya Ghai · Udari Madhuhshani · Naomi Leonard · Elad Hazan

Hall E #736

Keywords: [ T: Online Learning and Bandits ] [ OPT: Control and Optimization ]


Abstract:

We study the problem of multi-agent control of a dynamical system with known dynamics and adversarial disturbances. Our study focuses on optimal control without centralized precomputed policies, but rather with adaptive control policies for the different agents that are only equipped with a stabilizing controller. We give a reduction from any (standard) regret minimizing control method to a distributed algorithm. The reduction guarantees that the resulting distributed algorithm has low regret relative to the optimal precomputed joint policy. Our methodology involves generalizing online convex optimization to a multi-agent setting and applying recent tools from nonstochastic control derived for a single agent. We empirically evaluate our method on a model of an overactuated aircraft. We show that the distributed method is robust to failure and to adversarial perturbations in the dynamics.

Chat is not available.