The Structure of Learning
The Structure of Learning

Author: R. Allen Gardner

Publisher: Psychology Press

Published: 2013-06-17

Total Pages: 400

ISBN-13: 1134805217

DOWNLOAD EBOOK

Drawing together research and theory in ethology and psychology, this book offers a clear and provocative account of the ways in which living organisms learn. Throughout, the authors' focus is on the importance of operational definition. In lively prose, describing experiments in enough depth to involve readers in the drama of experimental method, they recount the history of scientists' attempts to answer basic questions, and show how one study builds on another. Although they present the major traditional positions, they demand that readers examine actual evidence, recognize weaknesses, and consider alternatives. This critical process leads to the delineation of a bottom up, feed forward model in contrast to the traditional top down, feed backward one. Recent research in robotics and fuzzy logic suggests ways in which artificial as well as living systems pursue bottom up, feed forward ethological solutions to practical problems. The authors' extended discussion of their exciting work teaching sign language to chimpanzees vividly illustrates the application of the basic principles of learning elucidated in the book.

Reinforcement Learning, second edition
Reinforcement Learning, second edition

Author: Richard S. Sutton

Publisher: MIT Press

Published: 2018-11-13

Total Pages: 549

ISBN-13: 0262352702

DOWNLOAD EBOOK

The significantly expanded and updated new edition of a widely used text on reinforcement learning, one of the most active research areas in artificial intelligence. Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms. This second edition has been significantly expanded and updated, presenting new topics and updating coverage of other topics. Like the first edition, this second edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new to the second edition, including UCB, Expected Sarsa, and Double Learning. Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods. Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.