Browsing by Author "Saldi, Naci"

Now showing 1 - 3 of 3

Open Access
Optimality of independently randomized symmetric policies for exchangeable stochastic teams with infinitely many decision makers
(Institute for Operations Research and the Management Sciences (INFORMS), 2022-08-24) Sanjari, S.; Saldi, Naci; Yüksel, S.
Open Access
Partially observed discrete-time risk-sensitive mean field games
(Birkhaeuser Science, 2022-06-07) Saldi, Naci; Başar, T.; Raginsky, M.
In this paper, we consider discrete-time partially observed mean-field games with the risk-sensitive optimality criterion. We introduce risk-sensitivity behavior for each agent via an exponential utility function. In the game model, each agent is weakly coupled with the rest of the population through its individual cost and state dynamics via the empirical distribution of states. We establish the mean-field equilibrium in the infinite-population limit using the technique of converting the underlying original partially observed stochastic control problem to a fully observed one on the belief space and the dynamic programming principle. Then, we show that the mean-field equilibrium policy, when adopted by each agent, forms an approximate Nash equilibrium for games with sufficiently many agents. We first consider finite-horizon cost function and then discuss extension of the result to infinite-horizon cost in the next-to-last section of the paper.
Open Access
Q-learning in regularized mean-field games
(Birkhaeuser Science, 2022-05-23) Anahtarci, B.; Kariksiz, C.D.; Saldi, Naci
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.