Learning Stationary Correlated Equilibria in Constrained General-Sum Stochastic Games
نویسندگان
چکیده
منابع مشابه
General-Sum Games: Correlated Equilibria
This lecture introduces a generalization of Nash equilibrium due to Aumann [1] known as correlated equilibrium, which allows for possible dependencies in strategic choices. A daily example of a correlated equilibrium is a traffic light: a red (green) signal suggests that cars should stop (go), and following each suggestion is of course rational. Following Aumann [2], we present two definitions ...
متن کاملFinding Correlated Equilibria in General Sum Stochastic Games
Often problems arise where multiple self-interested agents with individual goals can coordinate their actions to improve their outcomes. We model these problems as general sum stochastic games. We develop a tractable approximation algorithm for computing subgame-perfect correlated equilibria in these games. Our algorithm is an extension of standard dynamic programming methods like value iterati...
متن کاملAlmost Stationary (-Equilibria in Zero-Sum Stochastic Games
We show the existence of almost stationary (-equilibria, for all (H0, in zero-sum stochastic games with finite state and action spaces. These are (-equilibria with the property that, if neither player deviates, then stationary strategies are played forever with probability almost 1. The proof is based on the construction of specific stationary strategy pairs, with corresponding rewards equal to...
متن کاملAlgorithms for Nash Equilibria in General-Sum Stochastic Games
Over the past few decades the quest for algorithms to compute Nash equilibria in general-sum stochastic games has intensified and several important algorithms (cf. [9], [12], [16], [7]) have been proposed. However, they suffer from either lack of generality or are intractable for even medium sized problems or both. In this paper, we first formulate a non-linear optimization problem for stochast...
متن کاملTwo-Timescale Algorithms for Learning Nash Equilibria in General-Sum Stochastic Games
We consider the problem of finding stationary Nash equilibria (NE) in a finite discounted general-sum stochastic game. We first generalize a non-linear optimization problem from [9] to a general N player game setting. Next, we break down the optimization problem into simpler sub-problems that ensure there is no Bellman error for a given state and an agent. We then provide a characterization of ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Cybernetics
سال: 2016
ISSN: 2168-2267,2168-2275
DOI: 10.1109/tcyb.2015.2453165