Description
PyTorch 1.0 Reinforcement Learning Cookbook introduces you to reviews of important RL concepts and implementations of algorithms in PyTorch. Each chapter of the book walks you through the main type of RL method and its industry adopted applications. With the help of recipes with realistic examples, you will find it intriguing to enhance your knowledge and proficiency of RL techniques in areas such as dynamic programming, Monte Carlo methods, temporal difference and Q-learning, multi-armed bandit, function approximation, deep Q-Networks, and policy gradients - they are no more obscure as you thought.
