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 13 – TRPO, PPO, and ACKTR Methods

  1. The trust region implies the region where our actual function f(x) and approximated function are close together. So, we can say that our approximation will be accurate if our approximated function is in the trust region.
  2. TRPO is a policy gradient algorithm, and it acts as an improvement to policy gradient with baseline. TRPO tries to make a large policy update while imposing a KL constraint that the old policy and the new policy should not vary from each other too much. TRPO guarantees monotonic policy improvement, guaranteeing that there will always be a policy improvement on every iteration.
  3. Just like gradient descent, conjugate gradient descent also tries to find the minimum of the function; however, the search direction of conjugate gradient descent will be different from gradient descent and conjugate gradient descent attains convergence in N iterations.
  4. The update rule of TRPO is given as .
  5. PPO...