

#4870
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
Mentioned by 

when discussing the importance of accessible ML compute.


George Hotz

129 snips
Commoditizing the Petaflop — with George Hotz of the tiny corp
Mentioned by ![undefined]()

as a source of foundational knowledge in reinforcement learning.

Minqi Jiang

100 snips
#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)
Recommended by ![undefined]()

as a good introduction to reinforcement learning, although he notes it simplifies the subject.

Marcus Hutter

46 snips
#75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI
Mentioned by 

when discussing his journey into reinforcement learning.


David Silver

43 snips
#86 – David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning
Recommended by 

as the classic RL textbook, relevant to understanding RLHF.


Nathan Lambert

18 snips
The state of post-training in 2025
Recommended by ![undefined]()

as a fun and important read on reinforcement learning.

Tom Gilbert

AI: Open vs Closed + NeurIPS Reflections
Mentioned by ![undefined]()

as the author of the RL book, whose second part includes sections on average reward and why discounting should be deprecated.

Abhishek Naik

Abhishek Naik on Continuing RL & Average Reward