Reinforcement Learning, second edition cover

Reinforcement Learning, second edition

An Introduction (Adaptive Computation and Machine Learning series)

by Richard S. Sutton

Price৳ 400
Price৳ 400

Have a question? Ask on WhatsApp or Message on Messenger

Call 01963 822422 / 01817 506044 for help with your order

Reinforcement Learning by Richard S. Sutton is the foundational text on computational decision-making and agent-based trial-and-error learning. This updated second edition presents the core theoretical principles and algorithmic solutions that drive modern autonomous systems. It covers foundational dynamic programming methods through advanced deep policy gradients and actor-critic architectures.

What you will learn

  • Formulate decision problems using Markov Decision Processes and Bellman equations
  • Solve sequential control tasks using dynamic programming and policy iteration
  • Implement Monte Carlo and Temporal-Difference methods, including Q-learning and SARSA
  • Combine reinforcement learning with linear and nonlinear function approximation
  • Train continuous control models with policy gradient and actor-critic methods
  • Balance the exploration versus exploitation trade-off using bandit algorithms

Who this is for

Machine learning researchers, AI engineers, and graduate students building autonomous decision-making agents. Prior knowledge of multivariable calculus, probability, and basic Python programming is helpful.