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 5 – Understanding Temporal Difference Learning

  1. Unlike the Monte Carlo method, the Temporal Difference (TD) learning method makes use of bootstrapping so that we don't have to wait until the end of the episode to compute the value of a state.
  2. The TD learning algorithm takes the benefits of both the dynamic programming and the Monte Carlo methods into account. That is, just like the dynamic programming method, we perform bootstrapping so that we don't have to wait till the end of an episode to compute the state value or Q value and just like the Monte Carlo method, it is a model-free method, and so it does not require the model dynamics of the environment to compute the state value or Q value.
  3. The TD error can be defined as the difference between the target value and predicted value.
  4. The TD learning update rule is given as .
  5. In a TD prediction task, given a policy, we estimate the value function using the given policy. So, we...