Download Reinforcement Learning: An Introduction by Richard S. Sutton, Andrew G. Barto, Reinforcement learning is a computational approach to learning whereby an agent tries to maximise the entire amount of reward it receives once interacting with a complex, uncertain environment. in this book, Richard Sutton and andrew Barto offer a transparent and easy account of the key concepts and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the foremost recent developments and applications. the sole necessary mathematical background is familiarity with elementary ideas of probability. Download the pdf from below to explore all topics and start learning.


I Tabular Solution Methods
Multi-armed Bandits
Finite Markov Decision Processes
Dynamic Programming
Monte Carlo Methods
Temporal-Di↵erence Learning
n-step Bootstrapping
Planning and Learning with Tabular Methods

II Approximate Solution Methods
On-policy Prediction with Approximation
On-policy Control with Approximation
*Off-policy Methods with Approximation
Eligibility Traces
Policy Gradient Methods

III Looking Deeper
Applications and Case Studies