Efficient Regret Minimization in Non-Convex Games
نویسندگان
چکیده
We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and generalizes offline guarantees for convergence to an approximate local optimum. We give gradient-based methods that achieve optimal regret, which in turn guarantee convergence to equilibrium in this framework.
منابع مشابه
Random Walk Approach to Regret Minimization
We propose a computationally efficient random walk on a convex body which rapidly mixes to a time-varying Gibbs distribution. In the setting of online convex optimization and repeated games, the algorithm yields low regret and presents a novel efficient method for implementing mixture forecasting strategies.
متن کاملThe convex optimization approach to regret minimization
A well studied and general setting for prediction and decision making is regret minimization in games. Recently the design of algorithms in this setting has been influenced by tools from convex optimization. In this chapter we describe the recent framework of online convex optimization which naturally merges optimization and regret minimization. We describe the basic algorithms and tools at the...
متن کاملLogarithmic Regret Algorithms for Strongly Convex Repeated Games
Many problems arising in machine learning can be cast as a convex optimization problem, in which a sum of a loss term and a regularization term is minimized. For example, in Support Vector Machines the loss term is the average hinge-loss of a vector over a training set of examples and the regularization term is the squared Euclidean norm of this vector. In this paper we study an algorithmic fra...
متن کاملRegret Minimization in Non-Zero-Sum Games with Applications to Building Champion Multiplayer Computer Poker Agents
In two-player zero-sum games, if both players minimize their average external regret, then the average of the strategy profiles converges to a Nash equilibrium. For n-player general-sum games, however, theoretical guarantees for regret minimization are less understood. Nonetheless, Counterfactual Regret Minimization (CFR), a popular regret minimization algorithm for extensiveform games, has gen...
متن کاملIterated Regret Minimization in Game Graphs
Iterated regret minimization has been introduced recently by J.Y. Halpern and R. Pass in classical strategic games. For many games of interest, this new solution concept provides solutions that are judged more reasonable than solutions offered by traditional game concepts – such as Nash equilibrium –. In this paper, we investigate iterated regret minimization for infinite duration two-player qu...
متن کامل