arXiv research

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

Just as war is sometimes fallaciously represented as a zero sum game -- when in fact war is a negative sum game - stock market trading, a positive sum game over time, is often erroneously represented as a zero sum game. This is called the "zero sum fallacy" -- the erroneous belief that one trader in a stock market exch…

Gradient methods converge exponentially in concave network games.

Gradient Descent Ascent converges to von-Neumann solution in hidden zero-sum games.

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

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

GANs may not have Nash equilibria, but proximal training can find solutions.

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 studies competitive networks where teams aim to minimize their own objectives, adapting to each other's strategies.

Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.

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…

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

New game approximates mean curvature flow evolution.

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

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

We study the global convergence of policy optimization for finding the Nash equilibria (NE) in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of LQ games, viewing it as a nonconvex-nonconcave saddle-point problem in the policy space. Specifically, we show that despite its nonconve…

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…

This work finds mixed equilibria in zero-sum games using interacting particle dynamics.

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradi…

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

Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.

Paper proposes a mean-field gradient descent for zero-sum games, proving convergence to Nash equilibrium.

Study on convergence of Langevin dynamics for zero-sum games in probability distributions.

Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transitive, then self-play generates sequences of agents of increasing strength. However, nontransitive games, such as rock-paper-scissors, can ex…

Paper studies constrained control games with a novel approximation method.

Mutation improves FTRL convergence in zero-sum games.

Proposes a new training algorithm for zero-sum games to avoid convergence issues.

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

The paper solves investment problems with uncertain factors using game theory.

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

Algorithm learns Nash equilibria in stochastic games using entropy-regularized policies.

We study a wide class of non-convex non-concave min-max games that generalizes over standard bilinear zero-sum games. In this class, players control the inputs of a smooth function whose output is being applied to a bilinear zero-sum game. This class of games is motivated by the indirect nature of the competition in Ge…

Paper studies zero-sum games with noisy observations and identifies equilibrium conditions.

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

Study of $2 imes 2$ zero-sum games with noisy observations and commitments.

Many tasks in modern machine learning can be formulated as finding equilibria in \emph{sequential} games. In particular, two-player zero-sum sequential games, also known as minimax optimization, have received growing interest. It is tempting to apply gradient descent to solve minimax optimization given its popularity a…

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…

New algorithms converge faster to Nash equilibrium in zero-sum games with bandit feedback.

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

We consider a zero-sum continuous time stopping game in which the pay-off is revealed in the maximum of the two stopping times instead of the minimum, which is the case in Dynkin games.

Paper solves complex game theory problems with new equations.

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…

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

Paper analyzes robust strategies in a pension plan game with ambiguous financial markets.

Algorithm learns NE in imperfect information games with imperfect feedback.

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

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

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