Book Image

Deep Reinforcement Learning with Python - Second Edition

By : Sudharsan Ravichandiran
Book Image

Deep Reinforcement Learning with Python - Second Edition

By: Sudharsan Ravichandiran

Overview of this book

With significant enhancements in the quality and quantity of algorithms in recent years, this second edition of Hands-On Reinforcement Learning with Python has been revamped into an example-rich guide to learning state-of-the-art reinforcement learning (RL) and deep RL algorithms with TensorFlow 2 and the OpenAI Gym toolkit. In addition to exploring RL basics and foundational concepts such as Bellman equation, Markov decision processes, and dynamic programming algorithms, this second edition dives deep into the full spectrum of value-based, policy-based, and actor-critic RL methods. It explores state-of-the-art algorithms such as DQN, TRPO, PPO and ACKTR, DDPG, TD3, and SAC in depth, demystifying the underlying math and demonstrating implementations through simple code examples. The book has several new chapters dedicated to new RL techniques, including distributional RL, imitation learning, inverse RL, and meta RL. You will learn to leverage stable baselines, an improvement of OpenAI’s baseline library, to effortlessly implement popular RL algorithms. The book concludes with an overview of promising approaches such as meta-learning and imagination augmented agents in research. By the end, you will become skilled in effectively employing RL and deep RL in your real-world projects.
Table of Contents (22 chapters)
Other Books You May Enjoy

Chapter 6 – Case Study – The MAB Problem

  1. The Multi-Armed Bandit (MAB) problem is one of the classic problems in RL. A MAB is a slot machine where we pull the arm (lever) and get a payout (reward) based on some probability distribution. A single slot machine is called a one-armed bandit, and when there are multiple slot machines, it is called a MAB or k-armed bandit, where k denotes the number of slot machines.
  2. With the epsilon-greedy policy, we select the best arm with probability 1-epsilon, and we select the random arm with probability epsilon.
  3. In softmax exploration, the arm will be selected based on the probability. However, in the initial rounds we will not know the correct average reward of each arm, so selecting the arm based on the probability of average reward will be inaccurate in the initial rounds. So to avoid this we introduce a new parameter called T. T is called the temperature parameter.
  4. The upper confidence bound is computed...