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

On-Policy MC Control – Epsilon-Greedy

The algorithm for on-policy MC control with the epsilon-greedy policy is given as follows:

  1. Let total_return(s, a) be the sum of the return of a state-action pair across several episodes and N(s, a) be the number of times a state-action pair is visited across several episodes. Initialize total_return(s, a) and N(s, a) for all state-action pairs to zero and initialize a random policy .
  2. For M number of iterations:
    1. Generate an episode using policy
    2. Store all the rewards obtained in the episode in the list called rewards
    3. For each step t in the episode:

      If (st, at) is occurring for the first time in the episode:

      1. Compute the return of a state-action pair, R(st, at) = sum(rewards[t:]).
      2. Update the total return of the state-action pair as total_return(st, at) = total_return(st, at) + R(st, at).
      3. Update the counter as N(st, at) = N(st, at) + 1.
      4. ...