Timezone: »

 
Poster
Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games
Adrian Rivera Cardoso · Jacob Abernethy · He Wang · Huan Xu

Thu Jun 13 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #151
in Posters Thu »

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 for a fixed game matrix this can be easily reduced to solving a linear program. But when the payoff matrix evolves over time our goal is to find a sequential algorithm that can compete with, in a certain sense, the NE of the long-term-averaged payoff matrix. We design an algorithm with small NE regret--that is, we ensure that the long-term payoff of both players is close to minimax optimum in hindsight. Our algorithm achieves near-optimal dependence with respect to the number of rounds and depends poly-logarithmically on the number of available actions of the players. Additionally, we show that the naive reduction, where each player simply minimizes its own regret, fails to achieve the stated objective regardless of which algorithm is used. Lastly, we consider the so-called bandit setting, where the feedback is significantly limited, and we provide an algorithm with small NE regret using one-point estimates of each payoff matrix.

Keywords: Bandits · Game Theory and Mechanism Design · Online Learning

Author Information

Adrian Rivera Cardoso (Georgia Institute of Technology)
Jacob Abernethy (Georgia Institute of Technology)
He Wang (Georgia Institute of Technology)
Huan Xu (Georgia Tech)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors