- 博客(3)
- 资源 (1)
- 收藏
- 关注
原创 论文笔记:Dyna, an Integrated Architecture for Learning, Planning, and Reacting
文章基本概况标题:Dyna, an Integrated Architecture for Learning, Planning, and Reacting作者:Richard S. Sutton,强化学习教父,被认为是现代计算的强化学习创立者之一。他为该领域做出了许多重大贡献,包括:时间差分学习(temporal difference learning)、策略梯度方法(policy gr...
2019-07-30 11:01:16 873
原创 论文笔记:Software-Defined Networks with Mobile Edge Computing and Caching for Smart Cities
Software-Defined Networks with Mobile Edge Computing and Caching for Smart Cities: A Big Data Deep Reinforcement Learning Approach文章基本概况作者:Ying He, F. Richard Yu, Nan Zhao, Victor C.M. Leung, a...
2019-07-29 11:22:25 803
原创 北大信科夏令营机考题分类汇总
巧妙的方法1. 护林员盖房子(2019信科研究生上机测试)这个题目与leetcode85题为一题。利用了一个很玄妙的栈。#include <iostream>#include<string>#include <algorithm>#include <vector>#include<math.h>#include&...
2019-07-14 20:20:35 3971 3
Dyna, an Integrated Architecture for Learning, Planning, and Reacting
2019-07-29
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人