Q-learning in regularized mean-field games
Type :
Article
Publication Status :
Published
Access :
restrictedAccess
Abstract
In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algorithm without imposing restrictive convexity assumptions on the system components, which are needed in the absence of a regularization term.
Source :
Dynamic Games and Applications
Date :
2023-03
Volume :
13
Issue :
1
Publisher :
Springer
Collections
Share this page