Book Image

Hands-On Reinforcement Learning with Python

By : Sudharsan Ravichandiran
Book Image

Hands-On Reinforcement Learning with Python

By: Sudharsan Ravichandiran

Overview of this book

Reinforcement Learning (RL) is the trending and most promising branch of artificial intelligence. Hands-On Reinforcement learning with Python will help you master not only the basic reinforcement learning algorithms but also the advanced deep reinforcement learning algorithms. The book starts with an introduction to Reinforcement Learning followed by OpenAI Gym, and TensorFlow. You will then explore various RL algorithms and concepts, such as Markov Decision Process, Monte Carlo methods, and dynamic programming, including value and policy iteration. This example-rich guide will introduce you to deep reinforcement learning algorithms, such as Dueling DQN, DRQN, A3C, PPO, and TRPO. You will also learn about imagination-augmented agents, learning from human preference, DQfD, HER, and many more of the recent advancements in reinforcement learning. By the end of the book, you will have all the knowledge and experience needed to implement reinforcement learning and deep reinforcement learning in your projects, and you will be all set to enter the world of artificial intelligence.
Table of Contents (16 chapters)

Chapter 11

  1. The policy gradient is one of the amazing algorithms in RL where we directly optimize the policy parameterized by some parameter.
  2. Policy gradients are effective as we don't need to compute Q function to find the optimal policy.
  3. The role of the Actor network is to determine the best actions in the state by tuning the parameter, and the role of the Critic is to evaluate the action produced by the Actor.

  1. Refer section Trust region policy optimization
  2. We iteratively improve the policy and we impose a constraint that Kullback–Leibler (KL) divergence between old policy and a new policy is to be less than some constant. This constraint is called the trust region constraint.
  3. PPO modifies the objective function of TRPO by changing the constraint to a penalty a term so that we don't want to perform conjugate gradient.