Reinforcement learning is an approach for learning optimal action policy via experiencing, i.e. using observed reward in environment states. Reinforcement learning algorithms include adaptive dynamic programming, temporal difference learning and Q-learning[1]. Examples of successful applications of reinforcement learning are controller for sustained inverted flight on an autonomous helicopter [...

Interactions between dark matter and dark energy with a given equation of state are known to modify the cosmic dynamics. On the other hand, the strength of these interactions is subject to strong observational constraints. Here we discuss a model in which the transition from decelerated to accelerated expansion of the Universe arises as a pure interaction phenomenon. Various cosmological scenar...

The explosive growth in the availability of information is overwhelming traditional information management systems. Although individual pieces of information have become easy to nd, the larger context in which they exist has become harder to track. These contextual questions are ideally suited to visualization since the human visual system is remarkably adept at interpreting large quantities of...

This chapter describes the development of the E-News project which examined an interactive journalism approach in Rockhampton, Australia. This project provided an opportunity to examine how the introduction of this new technology into regional media and communication brings into question the traditional roles of the journalist, the editor, the graphic designer and the audience in the production...

Over the last decade, Computer Vision, branch of Artificial Intelligence aimed at understanding visual world, has evolved from simply recognizing objects in images to describing pictures, answering questions about images, aiding robots maneuver around physical spaces, and even generating novel content. As these tasks applications have modernized, so too reliance on more data, either for model t...