Back to Search
Start Over
Mixed-Strategy Learning With Continuous Action Sets.
- Source :
-
IEEE Transactions on Automatic Control . Jan2017, Vol. 62 Issue 1, p379-384. 6p. - Publication Year :
- 2017
-
Abstract
- Motivated by the recent applications of game-theoretical learning 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. We propose an actor-critic reinforcement learning algorithm that adapts mixed strategies over continuous action spaces. To analyze the algorithm, we extend the theory of finite-dimensional two-timescale stochastic approximation to a Banach space setting, and 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 other agents. [ABSTRACT FROM PUBLISHER]
Details
- Language :
- English
- ISSN :
- 00189286
- Volume :
- 62
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Automatic Control
- Publication Type :
- Periodical
- Accession number :
- 120459042
- Full Text :
- https://doi.org/10.1109/TAC.2015.2511930