Learning in Two‐Player Matrix Games
Howard M. Schwartz · 2014
This chapter examines the two-player stage game or the matrix game problem, where two players are learning how to play the game. In some cases they may be competing with each other, or they may be cooperating with the other. The chapter discusses the class of game, and focuses on three different games: matching pennies, rock-paper-scissors, and prisoners' dilemma. These are all called matrix games or stage games because there is no state transition involved. The chapter demonstrates how to compute the Nash equilibrium (NE) in competitive zero-sum games. It presents several algorithms that have gained popularity within the field of machine learning. The chapter focuses on the algorithms that have been used for learning how to choose the optimal actions when agents are playing matrix games.