Various supervised inference methods can be analyzed as convex duals of the generalized maximum entropy (MaxEnt) framework. Generalized MaxEnt aims to find a distribution that max...
In this paper we apply the recent notion of anytime universal intelligence tests to the evaluation of a popular reinforcement learning algorithm, Q-learning. We show that a general...
Abstract. Multigame playing agents are programs capable of autonomously learning to play new, previously unknown games. In this paper, we concentrate on the General Game Playing Co...
We consider graphical games in which edges are zero-sum games between the endpoints/players; the payoff of a player is the sum of the payoffs from each incident edge. We give a si...
Constantinos Daskalakis, Christos H. Papadimitriou
Abstract. We develop a probabilistic interpretation of non-linear component extraction in neural networks that activate their hidden units according to a softmaxlike mechanism. On ...