強化學習是一類重要的機器學習方法,在很多領域得到了成功的應用,*近幾年與深度學習結合起來,進一步推動了人工智能的發(fā)展?本書首先介紹了強化學習的基本原理,然后介紹典型的強化學習算法,包括時序差分? SARSA? Q-Learning? DeepQ-network? Double DQN?競爭網(wǎng)絡結構? Rainbow? Actor-Critic? A2C? A3C? TRPO和PPO等,每種算法基本上利用了主流的開源機器學習框架TensorFlow,使用Python編程進行實現(xiàn)?此外,還介紹了一些上述算法的應用?本書可以使讀者快速理解強化學習的基本知識,并通過簡單的案例加深對算法的理解?本書適合對強化學習感興趣的普通高校師生以及相關專業(yè)人員閱讀?Copyright ? Packt Publishing 2018First published in the English language under the title “Deep Learning with TensorFlow-SecondEdition- ( 9781788831109)”Copyright in the Chinese language( simplified characters) ? 2020 China Machine PreesThis title is published in China by China Machine Press with license from Packt Publishing Ltd.This edition is authorized for sale in China only , excluding Hong Kong SAR. Macao SAR and Taiwan.Unauthorized export of this edition is a violation of the Copyright Act. Violation of this Law is subjectto Civil and Criminal Penalties.