In this paper, based on recent scientific findings in the fields of neurology, evolutionary psychology and cognitive psychology we propose a software architecture and technology su...
This paper proposes the use of constructive ordinals as mistake bounds in the on-line learning model. This approach elegantly generalizes the applicability of the on-line mistake ...
We1 present a new actor-critic learning model in which a Bayesian class of non-parametric critics, using Gaussian process temporal difference learning is used. Such critics model ...
We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...
Given an adequate simulation model of the task environment and payoff function that measures the quality of partially successful plans, competition-based heuristics such as geneti...