arXiv research

New algorithm reduces online learning regret in uninformed Markov games.

Decentralized algorithm reduces regret and converges to Nash equilibrium in online congestion games.

DP-NCB algorithm ensures privacy and fairness in bandit decisions.

No-regret learning fails to converge to Nash equilibria in mixed strategies.

We argue that the existing regret matchings for Nash equilibrium approximation conduct "jumpy" strategy updating when the probabilities of future plays are set to be proportional to positive regret measures. We propose a geometrical regret matching which features "smooth" strategy updating. Our approach is simple, intu…

Algorithm finds Nash equilibria in complex games with function approximation.

ESCHER avoids importance sampling to estimate regret in large games.

The paper analyzes Q-learning in 2-player Markov games and provides gap-dependent logarithmic regret bounds.

Dynamic pricing policy converges to Nash equilibrium with low regret.

The paper tackles Nash-regret minimization in congestion games with bandit feedback.

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

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

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

This paper tackles no-regret learning for fair multi-agent social welfare optimization.

Algorithm learns fair division from noisy feedback in uncertain markets.

Novel algorithms for multi-agent reinforcement learning reduce sample complexity.

Motivated by the scarcity of accurate payoff feedback in practical applications of game theory, we examine a class of learning dynamics where players adjust their choices based on past payoff observations that are subject to noise and random disturbances. First, in the single-player case (corresponding to an agent tryi…

The paper tackles fair sharing of exploration costs across groups in online learning.

Paper solves learning imperfect-information games with fewer episodes.

We study multiplayer stochastic multi-armed bandit problems in which the players cannot communicate and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider two feedback models: a model in which the players can observe whether a collision has occurred an…

New RL algorithms find SNE in Markov games with myopic followers.

The CFR framework has been a powerful tool for solving large-scale extensive-form games in practice. However, the theoretical rate at which past CFR-based algorithms converge to the Nash equilibrium is on the order of $O(T^{-1/2})$, where $T$ is the number of iterations. In contrast, first-order methods can be used to …

We study the online saddle point problem, an online learning problem where at each iteration a pair of actions need to be chosen without knowledge of the current and future (convex-concave) payoff functions. The objective is to minimize the gap between the cumulative payoffs and the saddle point value of the aggregate …

Framework for games with uncertain parameters, ensuring no player can improve by changing strategy.

Models analyze strategic risk-taking in continuous action games.

Let $M$ and $N$ be Nash manifolds, and $f$ and $g$ Nash maps from $M$ to $N$. If $M$ and $N$ are compact and if $f$ and $g$ are analytically R-L equivalent, then they are Nash R-L equivalent. In the local case, $C^infty$ R-L equivalence of two Nash map germs implies Nash R-L equivalence. This shows a difference of Nash…

V-learning tackles multiagent reinforcement learning by reducing sample complexity.

Decentralized learning ensures stability in online queuing systems with packet rates above 1.

Nash's theorem proved with Günther's trick

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…

We explicitly solve the nonlinear PDE that is the continuous limit of dynamic programming of \emph{expert prediction problem} in finite horizon setting with $N=4$ experts. The \emph{expert prediction problem} is formulated as a zero sum game between a player and an adversary. By showing that the solution is $\mathcal{C…

Machine learning detects NASH patients from medical claims data.

Optimal geometric estimates for Kähler manifolds with bounded Nash entropy

This work tackles learning Markov games with adversarial opponents and achieves both average reward and exploitation.

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

Paper optimizes multi-agent learning in Markov games with generative model.

New approach tackles non-stationary multi-agent games with black-box methods.

The paper examines Nash equilibrium in GANs for stationary Gaussian processes.

New method finds all Nash equilibria via vector optimization.

The h-cobordism theorem is a noted theorem in differential and PL topology. A generalization of the h-cobordism theorem for possibly non simply connected manifolds is the so called s-cobordism theorem. In this paper, we prove semialgebraic and Nash versions of these theorems. That is, starting with semialgebraic or Nas…

Motivated by cognitive radios, stochastic multi-player multi-armed bandits gained a lot of interest recently. In this class of problems, several players simultaneously pull arms and encounter a collision - with 0 reward - if some of them pull the same arm at the same time. While the cooperative case where players maxim…

Motivated by economic applications such as recommender systems, we study the behavior of stochastic bandits algorithms under \emph{strategic behavior} conducted by rational actors, i.e., the arms. Each arm is a \emph{self-interested} strategic player who can modify its own reward whenever pulled, subject to a cross-per…

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

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…

The study characterizes Nash maps between semialgebraic sets and their properties.

A method is provided to resolve Lie algebroids with singularities.

A Nash game theory approach allocates capital requirements among financial institutions.

Inspired by Strotz's consistent planning strategy, we formulate the infinite horizon mean-variance stopping problem as a subgame perfect Nash equilibrium in order to determine time consistent strategies with no regret. Equilibria among stopping times or randomized stopping times may not exist. This motivates us to cons…