AI & ML
Learning monotone game-theoretic linear MPC
arXiv cs.SY0 views
arXiv:2611.17504v1 Announce Type: new Abstract: We propose a method to learn a game-theoretic model predictive control (GT-MPC) law by imitation from input and output data of a running multi-agent system. By interpreting the recorded inputs as the first moves of the equilibria of a game played by the agents, we learn the GT-MPC weights under hard input constraints and soft output constraints, without requiring the agents to reveal their objectives. We also impose that the resulting generalized Nash equilibrium (GNE) problem is strongly monotone, which ensures the existence and uniqueness of the equilibrium and, hence, that the learned GT-MPC law is well defined and can be evaluated efficiently online by variational GNE-seeking algorithms for linear-quadratic games. Moreover, strong monotonicity implies that the equilibrium is almost everywhere differentiable with respect to the references and the weights, which enables automatic differentiation for gradient-based optimization. In addition, we promote closed-loop stability of the unconstrained equilibrium feedback by incorporating a penalty that involves a jointly learned quadratic Lyapunov function. Learning a GT-MPC formulation enables us to explain the agents' objectives, reproduce their behavior in simulation in new scenarios, optimize their set-points, design mechanisms, and enforce additional constraints. A numerical example illustrates the approach.
Source:https://arxiv.org/abs/2611.17504PreviousRAZeR: Representation Aware Zonotope ReductionNextSub-Synchronous Control Interaction Risk of Large Data Center Loads: A Frequency-Scan Assessment with Cross-Model Validation
Related posts

Building trustworthy AI by fencing it in, not predicting it
0MIT Technology Review

Trump says it ‘certainly isn’t a bad idea’ for Jensen Huang to return to Nvidia
0The Verge

Sony’s PlayStation 5 accessories are cheaper ahead of Black Friday
0The Verge
One Question to a RAG Chatbot Leaked Another Customer's Secret Price
0dev.to
How to Work Out What Your Freelance Rate Should Be
0dev.to
Jensen Huang Is Gone. Now What?
0Wired