To describe phenomena that occur at different time scales, computational models of the
brain must incorporate different levels of abstraction. At time scales of approximately 1/3 of a …

New developments in AI and neuroscience are revitalizing the quest to understanding
natural intelligence, offering insight about how to equip machines with human-like …

Fascinating phenomena such as landmark vector cells and splitter cells are frequently
discovered in the hippocampus. Without a unifying principle, each experiment seemingly …

This book introduces a new approach to the study of systems, living or artificial, that can
learn from experience, and in so doing it indicates a new focus of activity within Artificial …

To date, reinforcement learning has mostly been studied solving simple learning tasks.
Reinforcement learning methods that have been studied so far typically converge slowly …

Dyna is an AI architecture that integrates learning, planning, and reactive execution.
Learning methods are used in Dyna both for compiling planning results and for updating a …

Reinforcement learning agents are adaptive, reactive, and self-supervised. The aim of this
dissertation is to extend the state of the art of reinforcement learning and enable its …

Evolutionary Robotics is a method for automatically generating artificial brains and
morphologies of autonomous robots. This approach is useful both for investigating the …

Neural network reinforcement learning methods are described and considered as a direct
approach to adaptive optimal control of nonlinear systems. These methods have their roots …

Learning provides a useful tool for the automatic design of autonomous robots. Recent
research on learning robot control has predominantly focused on learning single tasks that …