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)

Solving the frozen lake problem

If you haven't understood anything we have learned so far, don't worry, we will look at all the concepts along with a frozen lake problem.

Imagine there is a frozen lake stretching from your home to your office; you have to walk on the frozen lake to reach your office. But oops! There are holes in the frozen lake so you have to be careful while walking on the frozen lake to avoid getting trapped in the holes:

Look at the preceding diagram:

  • S is the starting position (home)
  • F is the frozen lake where you can walk
  • H are the holes, which you have to be so careful about
  • G is the goal (office)

Okay, now let us use our agent instead of you to find the correct way to reach the office. The agent's goal is to find the optimal path to go from S to G without getting trapped at H. How can an agent achieve this? We give +1 point as a reward...