• A finite set of states St summarizing the information the agent senses from the environment at every time step t ∈ {1, ..., T}.

• A set of actions At which the agent can perform at each time step t ∈ {1, ..., T} to interact with the environment.

• A set of transition probabilities between subsequent states which render the environment stochastic. Note: the probabilities are usually not explicitly modeled but the result of the stochastic nature of the financial asset’s price process.

• A reward (or return) function Rt which provides a numerical feedback value rt to the agent in response to its action At−1 = at−1 in state St−1 = st−1.

• A policy π which maps states to concrete actions to be carried out by the agent. The policy can hence be understood as the agent’s rules for how to choose actions.

• A value function V which maps states to the total (discounted) reward the agent can expect from a given state until the end of the episode (trading period) under policy π.

Given the above framework, the decision problem is formalized as finding the optimal policy π = π ∗ , i.e., the mapping from states to actions, corresponding to the optimal value function V ∗ - see also Dempster et al. (2001); Dempster and Romahi (2002):

  V (st) = max at E[Rt+1 + γV (St+1)|St = st ].(1)

Hereby, E denotes the expectation operator, γ the discount factor, and Rt+1 the expected immediate reward for carrying out action At = at in state St = st . Further, St+1 denotes the next state of the agent. The value function can hence be understood as a mapping from states to discounted future rewards which the agent seeks to maximize with its actions.

To solve this optimization problem, the Q-Learning algorithm (Watkins, 1989) can be applied, extending the above equation to the level of state-action tuples:

  Q (st , at) = E[Rt+1 + γ max at+1 Q (St+1, at+1)|St = st , At = at ].(2)

Hereby, the Q-value Q∗ (st , at) equals to the immediate reward for carrying out action At = at in state St = st plus the discounted future reward from carrying on in the best way possible.

The optimal policy π (the mapping from states to actions) then simply becomes:

  π (st) = max at Q (st , at) .(3)

i.e., in every state St = st , choose the action At = at that yields the highest Q-value. To approximate the Q-function during (online) learning, an iterative optimization is carried out with α denoting the learning rate - see also Sutton and Barto (1998) for further details:

  Q (st , at) ← (1 − α) Q (st , at) + α (rt+1 + γ max at+1 Q (st+1, at+1) ) . (4)

a survey for RL的更多相关文章

  1. (转)Applications of Reinforcement Learning in Real World

    Applications of Reinforcement Learning in Real World 2018-08-05 18:58:04 This blog is copied from: h ...

  2. 论文笔记系列-Neural Network Search :A Survey

    论文笔记系列-Neural Network Search :A Survey 论文 笔记 NAS automl survey review reinforcement learning Bayesia ...

  3. (zhuan) 一些RL的文献(及笔记)

    一些RL的文献(及笔记) copy from: https://zhuanlan.zhihu.com/p/25770890  Introductions Introduction to reinfor ...

  4. A Survey of Visual Attention Mechanisms in Deep Learning

    A Survey of Visual Attention Mechanisms in Deep Learning 2019-12-11 15:51:59 Source: Deep Learning o ...

  5. Generalizing from a Few Examples: A Survey on Few-Shot Learning 小样本学习最新综述 | 三大数据增强方法

    目录 原文链接:小样本学习与智能前沿 01 Transforming Samples from Dtrain 02 Transforming Samples from a Weakly Labeled ...

  6. 知识图谱顶刊综述 - (2021年4月) A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

    知识图谱综述(2021.4) 论文地址:A Survey on Knowledge Graphs: Representation, Acquisition, and Applications 目录 知 ...

  7. SharePoint 2010 Survey的Export to Spreadsheet功能怎么不见了?

    背景信息: 最近用户报了一个问题,说他创建的Survey里将结果导出成Excel文件(Export to spreadsheet)的按钮不见了. 原因排查: 正常情况下,这个功能只存在于SharePo ...

  8. 中间值为什么为l+(r-l)/2,而不是(l+r)/2

    二分法的算法中,我们看到一些代码里取中间值: MID=l+(r-l)/2; 为什么是这个呢?不就是(l+r)/2吗?为什么要多此一举呢? 其实还是有不一样的,看看他们的区别吧: l,r是指针的时候只能 ...

  9. SharePoint Tricks - Survey

    1. SharePoint 2010中,在Survey的问题框中输入HTML代码可以用于插入图片或者链接,具体方法为: 1.1 在问题框中输入html, 1.2 在New Form和Edit Form ...

随机推荐

  1. ue4 enable input

    actor:  enable input 这个可以使多个actor接收输入 pawn: possese pawn使用enable input是不生效的 貌似不允许多个pawn同时接收输入,可以考虑直接 ...

  2. Unity手游之路自动寻路Navmesh之入门

    http://blog.csdn.net/janeky/article/details/17457533 现在的大部分mmo游戏都有了自动寻路功能.点击场景上的一个位置,角色就会自动寻路过去.中间可能 ...

  3. Codevs 2765 隐形的翅膀

    2765 隐形的翅膀   题目描述 Description 天使告诉小杉,每只翅膀都有长度,两只翅膀的长度之比越接近黄金分割比例(黄金分割比= 0.6180339887498949),就越完美. 现在 ...

  4. openinstall渠道统计工具介绍

    大家好,今天给大家介绍一下如何使用openinstall 来实现APP 渠道统计,做运营推广的朋友应该对渠道统计并不陌生,之前一般都是让技术的同事打渠道包方式进行渠道统计,而且只有安卓才能打渠道包.o ...

  5. Netty源码分析(七):初识ChannelPipeline

    ChannelPipeline单看名称就可以知道Channel的管道.本篇将结合它的默认实现类DefaultChannelPipeline来对它做一个简单的介绍. 示例图 上图是官方提供的Channe ...

  6. java 多线程下载文件并实时计算下载百分比(断点续传)

    多线程下载文件 多线程同时下载文件即:在同一时间内通过多个线程对同一个请求地址发起多个请求,将需要下载的数据分割成多个部分,同时下载,每个线程只负责下载其中的一部分,最后将每一个线程下载的部分组装起来 ...

  7. 基于Vue的省市区三级联动插件

    官网地址:https://distpicker.uine.org/ 安装: npm install v-distpicker --save 局部注册: import VDistpicker from ...

  8. System.Span, System.Memory,还有System.IO.Pipelines

    System.Span, System.Memory,还有System.IO.Pipelines 使用高性能Pipelines构建.NET通讯程序 .NET Standard支持一组新的API,Sys ...

  9. Net Core构建Angular4应用程序

    在Visual Studio 2017中使用Asp.Net Core构建Angular4应用程序   前言 Visual Studio 2017已经发布了很久了.做为集成了Asp.Net Core 1 ...

  10. shell 发送Post请求,并获取状态码

    #!/bin/bash aa=$ result=$(curl -H "Content-type: application/json" -X POST -o /dev/null -s ...