Game-theoretical control with continuous action sets
Perkins, Steven, Mertikopoulos, Panayotis, Leslie, David S.
Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets, and we propose an actor-critic reinforcement learning algorithm that provably converges to equilibrium in this class of problems. The method employed is to analyse the learning process under study through a mean-field dynamical system that evolves in an infinite-dimensional function space (the space of probability distributions over the players' continuous controls). To do so, we extend the theory of finite-dimensional two-timescale stochastic approximation to an infinite-dimensional, Banach space setting, and we prove that the continuous dynamics of the process converge to equilibrium in the case of potential games. These results combine to give a provably-convergent learning algorithm in which players do not need to keep track of the controls selected by the other agents.
Dec-1-2014
- Country:
- Europe > United Kingdom (0.28)
- Genre:
- Research Report (1.00)
- Industry:
- Energy > Power Industry (0.46)
- Technology: