Learning Parametric Closed-Loop Policies for Markov Potential Games
share
Multiagent systems where the agents interact among themselves and with an stochastic environment can be formalized as stochastic games. We study a subclass, named Markov potential games (MPGs), that appear often in economic and engineering applications when the agents share some common resource. We consider MPGs with continuous state-action variables, coupled constraints and nonconvex rewards. Previous analysis are only valid for very simple cases (convex rewards, invertible dynamics, and no coupled constraints); or considered deterministic dynamics and provided open-loop (OL) analysis, studying strategies that consist in predefined action sequences. We present a closed-loop (CL) analysis for MPGs and consider parametric policies that depend on the current state and where agents adapt to stochastic transitions. We provide verifiable, sufficient and necessary conditions for a stochastic game to be an MPG, even for complex parametric functions (e.g., deep neural networks); and show that a CL Nash equilibrium (NE) can be found (or at least approximated) by solving a related optimal control problem (OCP). This is useful since solving an OCP---a single-objective problem---is usually much simpler than solving the original set of coupled OCPs that form the game---a multiobjective control problem. This is a considerable improvement over previously standard approach. We illustrate the theoretical contributions with an example by applying our approach to a noncooperative communications engineering game. We then solve the game with a deep reinforcement learning algorithm that learns policies that closely approximates an exact variational NE of the game.
READ FULL TEXT