Linearly Solvable Continuous-Time General-Sum Stochastic Differential Games
This provides a method for efficiently solving multi-agent spatial conflicts like congestion avoidance, but it appears incremental as it builds on existing transformations and methods for specific game types.
The paper tackles the problem of solving continuous-time, finite-player stochastic general-sum differential games by introducing a class that admits solutions through an exact linear PDE system, resulting in efficient, grid-free computation of feedback Nash equilibrium strategies via the Feynman-Kac path integral method to overcome the curse of dimensionality.
This paper introduces a class of continuous-time, finite-player stochastic general-sum differential games that admit solutions through an exact linear PDE system. We formulate a distribution planning game utilizing the cross-log-likelihood ratio to naturally model multi-agent spatial conflicts, such as congestion avoidance. By applying a generalized multivariate Cole-Hopf transformation, we decouple the associated non-linear Hamilton-Jacobi-Bellman (HJB) equations into a system of linear partial differential equations. This reduction enables the efficient, grid-free computation of feedback Nash equilibrium strategies via the Feynman-Kac path integral method, effectively overcoming the curse of dimensionality.