BriefGPT.xyz
Sep, 2016
强化学习中任务规范的统一
Unifying task specification in reinforcement learning
HTML
PDF
Martha White
TL;DR
介绍了一种RL任务形式化的方法，通过简单的构造实现了不同任务设置的统一，包括状态转移折扣的概括；并拓展了标准学习构造和部分理论结果，提供了一个可理解和可靠的形式化框架来构建理论和简化算法使用和开发。
Abstract
reinforcement learning
tasks are typically specified as
markov decision processes
. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning ob
→