In this paper we present TDLEAF( ), a variation on the TD( ) algorithm that enables it to be used in conjunction with game-tree search. We present some experiments in which our che...
Abstract. We consider Reinforcement Learning for average reward zerosum stochastic games. We present and analyze two algorithms. The first is based on relative Q-learning and the ...
We present a new algorithm for Unique Games which is based on purely spectral techniques, in contrast to previous work in the area, which relies heavily on semidefinite programmi...
Abstract. We consider two-person zero-sum stochastic mean payoff games with perfect information, or BWR-games, given by a digraph G = (V = VB VW VR, E), with local rewards r : E R...
Endre Boros, Khaled M. Elbassioni, Vladimir Gurvic...
This paper experimentally evaluates multiagent learning algorithms playing repeated matrix games to maximize their cumulative return. Previous works assessed that Qlearning surpas...