Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids

ArXi:2604.01830v1 Announce Type: new Topology control for power grid operation is a challenging sequential decision making problem because the action space grows combinatorially with the size of the grid and action evaluation through simulation is computationally expensive. We propose a physics-informed Reinforcement Learning framework that combines semi-Marko control with a Gibbs prior, that encodes the system's physics, over the action space.