Stability and Sensitivity Analysis for Objective Misspecifications Among Model Predictive Game Controllers
This work addresses the problem of ensuring reliable multi-agent control in robotics or autonomous systems when agents have inaccurate models of each other's objectives, representing an incremental advance in game-theoretic control analysis.
The paper analyzes the stability and sensitivity of multi-agent systems where agents use model predictive game controllers with potentially misspecified objectives, providing criteria for stability and quantifying equilibrium sensitivity to game parameters.
Model-based multi-agent control requires agents to possess a model of the behavior of others to make strategic decisions. Solution concepts from game theory are often used to model the emergent collective behavior of self-interested agents and have found active use in multi-agent control design. Model predictive games are a class of controllers in which an agent iteratively solves a finite-horizon game to predict the behavior of a multi-agent system and synthesize their own control action. When multiple agents implement these types of controllers, there may exist misspecifications in the respective game models embedded in their controllers, stemming from inaccurate estimates or conjectures of other agents' objectives. This paper analyzes the resulting prediction misalignments and their effects on the system's behavior. We provide criteria for the stability of multi-agent dynamic systems with heterogeneous model predictive game controllers, and quantify the sensitivity of the equilibria to individual agents' game parameters.