Reinforcement Learning and Stochastic Optimization

强化学习与随机优化:顺序决策的统一框架

运筹学

售   价:
1188.00
作      者
出  版 社
出版时间
2022年02月24日
装      帧
精装
ISBN
9781119815037
复制
页      码
1136
语      种
英文
综合评分
暂无评分

该图书目前无货

  • 图书详情
  • 目次
  • 买家须知
  • 书评(0)
  • 权威书评(0)
图书简介
This book lays the required unifying foundation for sequential decision problems every community can use and refer to. It begins with an introductory section which includes information on unified frameworks, the work of communities in decision-making, sequential learning, and major problem classes in stochastic optimization. The remainder of the book is organized around two major problem classes: state-independent problems (chapter 5-7), and state-dependent problems (chapter 8-onward). In later chapters the author describes a new classification system of functions for making decisions which involves the creation of four new classes of policies: policy function approximations (PFAs), cost function approximations (CFAs), value function approximations (VFAs), and lookahead approximations (DLAs).
本书暂无推荐
本书暂无推荐
看了又看
  • 上一个
  • 下一个