We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-b...
We develop a normative theory of interaction-negotiation in particular--among self-interested computationally limited agents where computational actions are game-theoretically tre...
We consider the problem of finding the best arm in a stochastic multi-armed bandit game. The regret of a forecaster is here defined by the gap between the mean reward of the optim...
The paper addresses limitations of strictly interactive theories of videogame genre, proposes a supplementary, historicist inter-media alternative, and interprets the videogame Ka...
Abstract. This paper is devoted to discuss a general tendency in contextualism which is known as "radical contextualism". In the first part I state the well known paradox...