Throughout this thesis, I develop the idea that the problem of learning good temporal
abstractions in reinforcement learning is intimately tied to a kind of representation learning …

Primary Examiner—Omar Fernandez Rivas Related US Application Data(74) Attorney,
Agent, or Firm—Brown Rudnick LLP (60) Provisional application No. 61/045,664, filed on …

This paper shows how a single mechanism allows knowledge to be constructed layer by
layer directly from an agent's raw sensorimotor stream. This mechanism, the General Value …

Experience is the temporal sequence of sensations and actions that are the inputs and
outputs of an intelligent agent. This thesis identifies and develops two ideas that arise from …

In order to represent state in controlled, partially observable, stochastic dynamical systems,
some sort of sufficient statistic for history is necessary. Predictive representations of state …

The concept of state is central to dynamical systems. In any timeseries problem—such as
filtering, planning or forecasting—models and algorithms summarize important information …

The idea of temporal abstraction, ie learning, planning and representing the world at
multiple time scales, has been a constant thread in AI research, spanning sub-fields from …

Multi-agent systems draw together a number of significant trends in modern technology:
ubiquity, decentralisation, openness, dynamism and uncertainty. As work in these fields …

In this thesis we consider the task of catching a moving target with multiple pursuers, also
known as the “Pursuit Game”, in which coordination among the pursuers is critical. Our …

What knowledge is and how it is represented are important questions of cognition, and the
debate about how to understand knowledge in biological and artificial agents is not likely to …