Deep Reinforcement Learning Hands-On

Maxim Lapan is a deep learning enthusiast and independent researcher. His background and 15 years' work expertise as a software developer and a systems architect lays from low-level Linux kernel driver development to performance optimization and design of distributed applications working on thousands of servers. With vast work experiences in big data, Machine Learning, and large parallel distributed HPC and nonHPC systems, he has a talent to explain a gist of complicated things in simple words and vivid examples. His current areas of interest lie in practical applications of Deep Learning, such as Deep Natural Language Processing and Deep Reinforcement Learning. Maxim lives in Moscow, Russian Federation, with his family, and he works for an Israeli start-up as a Senior NLP developer.

Publisher's Note: This edition from 2018 is outdated and not compatible with any of the most recent updates to Python libraries. A new third edition, updated for 2020 with six new chapters that include multi-agent methods, discrete optimization, RL in robotics, and advanced exploration techniques is now available.This practical guide will teach you how deep learning (DL) can be used to solve complex real-world problems.Key FeaturesExplore deep reinforcement learning (RL), from the first principles to the latest algorithmsEvaluate high-profile RL methods, including value iteration, deep Q-networks, policy gradients, TRPO, PPO, DDPG, D4PG, evolution strategies and genetic algorithmsKeep up with the very latest industry developments, including AI-driven chatbotsBook DescriptionDeep Reinforcement Learning Hands-On is a comprehensive guide to the very latest DL tools and their limitations. You will evaluate methods including Cross-entropy and policy gradients, before applying them to real-world environments. Take on both the Atari set of virtual games and family favorites such as Connect4.The book provides an introduction to the basics of RL, giving you the know-how to code intelligent learning agents to take on a formidable array of practical tasks. Discover how to implement Q-learning on 'grid world' environments, teach your agent to buy and trade stocks, and find out how natural language models are driving the boom in chatbots.What you will learnUnderstand the DL context of RL and implement complex DL modelsLearn the foundation of RL: Markov decision processesEvaluate RL methods including Cross-entropy, DQN, Actor-Critic, TRPO, PPO, DDPG, D4PG and othersDiscover how to deal with discrete and continuous action spaces in various environmentsDefeat Atari arcade games using the value iteration methodCreate your own OpenAI Gym environment to train a stock trading agentTeach your agent to play Connect4 using AlphaGo ZeroExplore the very latest deep RL research on topics including AI-driven chatbotsWho this book is forSome fluency in Python is assumed. Basic deep learning (DL) approaches should be familiar to readers and some practical experience in DL will be helpful. This book is an introduction to deep reinforcement learning (RL) and requires no background in RL.