In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be use...
In this paper, we present a replanning algorithm for a decision-theoretic hierarchical planner, illustrate the experimental methodology we designed to investigate its performance,...
The JavaScript language is used to enhance the clientside display of web pages. JavaScript code is downloaded into browsers and executed on-the-fly by an embedded interpreter. Br...
Many virtual communities involve ongoing discussions, with large numbers of users and established, if implicit rules for participation. As new users enter communities like this, b...
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...