#5168
Mentioned in 6 episodes
Reinforcement Learning: An Introduction
Second Edition
Book • 2018
This second edition of 'Reinforcement Learning: An Introduction' by Richard S. Sutton and Andrew G. Barto provides a clear and simple account of the field's key ideas and algorithms.
The book is significantly expanded and updated, including new topics such as artificial neural networks, the Fourier basis, and expanded treatment of off-policy learning and policy-gradient methods.
It also includes new chapters on the relationships between reinforcement learning and psychology/neuroscience, as well as updated case studies on AlphaGo, AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy.
The final chapter discusses the future societal impacts of reinforcement learning.
The book is significantly expanded and updated, including new topics such as artificial neural networks, the Fourier basis, and expanded treatment of off-policy learning and policy-gradient methods.
It also includes new chapters on the relationships between reinforcement learning and psychology/neuroscience, as well as updated case studies on AlphaGo, AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy.
The final chapter discusses the future societal impacts of reinforcement learning.
Mentioned by
Mentioned in 6 episodes
Recommended by Marcus Hutter as a good introduction to reinforcement learning, although he notes it simplifies the subject.
46 snips
#75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI
Mentioned by Abhishek Naik as the author of the RL book, whose second part includes sections on average reward and why discounting should be deprecated.
Abhishek Naik on Continuing RL & Average Reward
