arXiv research

Gradient methods converge exponentially in concave network games.

New algorithm finds near-optimal policies efficiently in zero-sum games.

New game approximates mean curvature flow evolution.

New assumptions and algorithm solve offline two-player zero-sum Markov games.

Study proposes new OPE estimators for two-player zero-sum games.

We consider the problem of two-player zero-sum games. This problem is formulated as a min-max Markov game in the literature. The solution of this game, which is the min-max payoff, starting from a given state is called the min-max value of the state. In this work, we compute the solution of the two-player zero-sum game…

Study Nash equilibrium in non-zero-sum game with Bermudan strategies.

Optimal algorithm for two-player zero-sum games with linear parameterization.

The paper explores how regularization can lead to convergence in imperfect information games.

Gradient-based methods for games suffer from discrete update steps that cause drift, affecting performance.

Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.

Research tackles alliance formation in many-player zero-sum games, showing reinforcement learning fails but a contract mechanism can help.

Algorithm learns NE in imperfect information games with imperfect feedback.

A geometric approach to differential game theory is illustrated. The parallel pursuit is considered as a two-player zero-sum differential game. The optimal strategies of each player is designed based on Riemann-Finsler geometry. Our approach incorporates a closed loop optimal control and the presentation is familiar wi…

We consider two-player non-zero-sum stopping games in discrete time. Unlike Dynkin games, in our games the payoff of each player is revealed after both players stop. Moreover, each player can adjust her own stopping strategy according to the other player's action. In the first part of the paper, we consider the game wh…

Method identifies mixed Nash equilibria in high dimensions for training mixtures of GANs.

Mutation improves FTRL convergence in zero-sum games.

This paper studies a 2-players zero-sum Dynkin game arising from pricing an option on an asset whose rate of return is unknown to both players. Using filtering techniques we first reduce the problem to a zero-sum Dynkin game on a bi-dimensional diffusion $(X,Y)$. Then we characterize the existence of a Nash equilibrium…

A RL approach finds Nash equilibrium for turn-based zero-sum games.

Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm is shown to find an $ε$-optimal strategy using sample size linear to the number …

Study learns optimal strategies in imperfect information games with self-play.

Algorithm learns from changing zero-sum games with no regret.

New algorithm improves sample efficiency for zero-sum Markov games.

Paper develops efficient algorithms for zero-sum Markov games with general function classes.

Transformers learn to play games in-context, proving Nash equilibrium.

In this paper, we settle the sampling complexity of solving discounted two-player turn-based zero-sum stochastic games up to polylogarithmic factors. Given a stochastic game with discount factor $γ\in(0,1)$ we provide an algorithm that computes an $ε$-optimal strategy with high-probability given $\tilde{O}((1 - γ)^{-3}…

We propose local symplectic surgery, a two-timescale procedure for finding local Nash equilibria in two-player zero-sum games. We first show that previous gradient-based algorithms cannot guarantee convergence to local Nash equilibria due to the existence of non-Nash stationary points. By taking advantage of the differ…

Paper solves complex game theory problems with new equations.

We develop an option pricing model based on a tug-of-war game. This two-player zero-sum stochastic differential game is formulated in the context of a multi-dimensional financial market. The issuer and the holder try to manipulate asset price processes in order to minimize and maximize the expected discounted reward. W…

Pessimistic model-based algorithm finds Nash equilibria in zero-sum Markov games from offline data.

This paper optimizes model-based RL for two-player zero-sum games with near-optimal sample complexity.

We study the problem of repeated play in a zero-sum game in which the payoff matrix may change, in a possibly adversarial fashion, on each round; we call these Online Matrix Games. Finding the Nash Equilibrium (NE) of a two player zero-sum game is core to many problems in statistics, optimization, and economics, and fo…

Paper solves learning imperfect-information games with fewer episodes.

Unified framework for estimating reward functions in competitive games.

Algorithm finds Nash equilibria in complex games with function approximation.

DREAM learns optimal strategies in imperfect games without needing a simulator.

We study optimal behavior of energy producers under a CO_2 emission abatement program. We focus on a two-player discrete-time model where each producer is sequentially optimizing her emission and production schedules. The game-theoretic aspect is captured through a reduced-form price-impact model for the CO_2 allowance…

Improved model-based reinforcement learning for multi-agent Markov games.

Paper tackles multiplayer symmetric games, securing equal share for n players.

A new multi-armed bandit framework with credal sets for uncertain outcomes.

New algorithms achieve logarithmic regret in KL-regularized Markov games.

New approach improves robustness of deep neural networks without overfitting.

A method learns to solve multilevel combinatorial problems with two players.

A large body of research is currently investigating on the connection between machine learning and game theory. In this work, game theory notions are injected into a preference learning framework. Specifically, a preference learning problem is seen as a two-players zero-sum game. An algorithm is proposed to incremental…

Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models. Cost-sensitive predictions are then achieved via a final processing step in the fe…

Efficient reinforcement learning for simultaneous-move zero-sum games using optimistic value iteration.

We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a two-player zero-sum game. In this new formulation, both players simultaneously play the s…

Policy gradient method proves convergence in imperfect-information games.