In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow or infeasible when RL agents begin with no prior knowledge. The key insight behind "transfer learning" is that generalization may occur not only within tasks, but also across tasks. While transfer has been studied in the psychological literature for many years, the RL community has only recently...

Since the year 2000 the ESA Cluster mission has been investigating the small-scale structures and processes of the Earth's plasma environment, such as those involved in the interaction between the solar wind and the magnetospheric plasma, in global magnetotail dynamics, in cross-tail currents, and in the formation and dynamics of the neutral line and of plasmoids.

This book contains presentations made at the 15th Cluster workshop held in March 2008. It also presents several articles about the Cluster Active Archive and its datasets, a few overview papers on the Cluster mission, and...

Structured directly around the specification of the OCR, this is the definitive textbook for students of Advanced Subsidiary or Advanced Level courses. The updated third edition covers all the necessary topics for Philosophy of Religion in an enjoyable student-friendly fashion. Each chapter includes:



a list of key issues


OCR specification checklist


explanations of key terminology


overviews of key scholars and theories


self-test review and exam practice questions.


To maximise students’ chances of success, the book contains a section dedicated to answering examination questions....