Download Reinforcement Learning and Optimal Control pdf by Dimitri P. Bertsekas, The purpose of the book is to consider large and difficult multistage decision issues, which can be resolved in principle by dynamic programming and optimal control, however their precise solution is computationally intractable. we discuss solution methods that rely on approximations to produce suboptimal policies with adequate performance. Download the pdf from below to explore all topics and start learning.


1 Principle of Optimality
2 Approximation in Value Space
3 Approximation in Policy Space
4 Model-Free Methods and Simulation
5 Policy Improvement, Rollout, and Self-Learning
6 Approximate Policy Improvement, Adaptive Simulation, and Q-Learning
7 Features, Approximation Architectures, and Deep Neural Nets
8 Incremental and Stochastic Gradient Optimization
9 Direct Policy Optimization: A More General Approach
10 Gradient and Random Search Methods for Direct Policy Optimization