Distributional Reinforcement Learning

Distributional Reinforcement Learning

简介:

分布式强化学习的第一个综合指南,为从概率角度思考决策提供了一种新的数学形式主义。分布式强化学习是一种新的数学形式主义,用于思考决策。除了强化学习和期望值的常见方法之外,它还关注作为代理选择的结果而获得的总回报或回报-特别是从概率的角度来看,这种回报是如何表现的。

英文简介:

The first comprehensive guide to distributional reinforcement learning, providing a new mathematical formalism for thinking about decisions from a probabilistic perspective.

Distributional reinforcement learning is a new mathematical formalism for thinking about decisions. Going beyond the common approach to reinforcement learning and expected values, it focuses on the total reward or return obtained as a consequence of an agent's choices—specifically, how this return behaves from a probabilistic perspective.

书名
Distributional Reinforcement Learning
译名
分布式强化学习
语言
英语
年份
2023
页数
385页
大小
8.05 MB
标签
  • 强化学习
  • 机器学习
  • 下载
    pdf iconDistributional Reinforcement Learning.pdf
    密码
    65536

    最后更新:2025-04-12 23:55:04

    ←Probabilistic Machine Learning: Advanced Topics

    →Reinforcement Learning: Theory and Algorithms