The significantly expanded and updated new edition of a widely used text on reinforcement learning, one of the most active research areas in artificial intelligence.
Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while inte...
The significantly expanded and updated new edition of a widely used text on reinforcement learning, one of the most active research areas in artificial intelligence.
Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms. This second edition has been significantly expanded and updated, presenting new topics and updating coverage of other topics.
Like the first edition, this second edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new to the second edition, including UCB, Expected Sarsa, and Double Learning. Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods. Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.
作者简介
· · · · · ·
Richard S. Sutton is Professor of Computing Science and AITF Chair in Reinforcement Learning and Artificial Intelligence at the University of Alberta, and also Distinguished Research Scientist at DeepMind.
Newcomers to reinforcement learning are sometimes surprised that the rewards -- which define of the goal of learning -- are computed in the environment rather than in the agent. Certainly most ultimate goals for animals are recognized by computations occuring inside their body: by sensors for recognizing food, hunger, pain and pleasure. Nevertheless, as we discussed in the previous section, one can redraw the agent-environment interface in such a way that these parts of the body are considered to be outside of the agent. ... For our purpose, it is convenient to place the boundary of the learning agent not at the limit of its physical body, but at the limit of its control. (查看原文)
James
The MIT Press1998版
eigenstate
电子工业出版社2019版
人生研究系主任
4 有用 注销倒计时 2019-06-06 00:12:40
可以交流一下exercise的答案?
0 有用 小小小小的火 2023-03-03 12:08:16 安徽
看过30%。非此方向的人，只是需要使用一点强化学习的内容，但这本书给自己一种醍醐灌顶的感觉，虽然可能要无限搁置了。
2 有用 苏夫佳 2022-12-19 17:55:38 重庆
这本书涵盖了很多rl的推导以及技术细节，有种发RL paper必备神器的感觉，但是有点美中不足的是有些地方明明一个公式带过的却有一大段文字描述，偏偏这些文字描述又只是把公式直白翻译了一遍对深入理解却没有太大帮助
0 有用 儒豪 2023-08-05 14:18:46 上海
根据Rich Sutton主页的两门课程来很好学 很大补
0 有用 PhoeniX_ReminD 2024-04-15 12:38:15 美国
不涉及数学的部分还算可以，涉及数学的部分不够清晰