着手开篇

写在前面

朋友你好！不论你是因为何种原因点开了这篇博客，都是我的荣幸！
此时落笔的我是一名大三学生，通信工程专业，已经在CSDN中“潜伏”了一段时间，在各种原因的驱使下（以前其实就是懒），我决定着手写写博客，对自己的经历与知识做一些些总结。如果有机会，希望能有与各位大神相互交流学习的机会；当然，如果我的内容能给你带来哪怕一点点启发，我会感到非常荣幸！
为了能使内容变得更加简洁，我会陆续开一些专题，如果你也有相同的兴趣，欢迎来访交流噢！

专题

随笔

沉淀和总结还是很重要的，这个专题中我会将近期的想法和状态写入其中。类似于说说和朋友圈，暂且把这个专题分出来，在里面说些想说的话吧。

PTA练习

PTA是PAT考试的练习平台。PAT是浙大计算机与科学学院组织的统一考试，如果有志于冲浙大计算机系的同学，可以多多关注一下。最近我正在pta平台上刷算法题，在练习的过程中发现对算法还是有点生疏了，想来上次系统地练习算法还是在大二上数据结构的时候，真的是太懒了，当时也是因为没有及时总结的习惯，所以效果也不是太好，哈哈哈哈哈哈哈哈哈，就当成是一个教训吧。
在这个专题中，我会记录一些练习过程中遇到的有意思的事，或许是一些小tips，或许是解决bug的过程，亦或是一些确实解决不了的问题，希望有大神看到了能给小弟指点迷津，不胜感激！！！

Reinforcement Learning

In this section, I will record some knowledge acquired in the learning process of RL, including personal understanding of the theories, reading notes and Implementation of the algorithm. The book I have been reading is Reinforcement Learning: An Introduction(The second edition), which is also considered the bible of the RL field.
Because of the need to read English literature in my daily study, and as one of the methods to train the English writing ability, I’ll try to arrange the section with pure English. If you have the same interests on RL, welcome to read my articles, and as I am also a beginner, I hope to get some advice if any mistakes occur in the article, I’ll treat any of them seriously!
Due to my limited programming ability, there will be some quotes in the article, which I will indicate in the “References” part, and I solemnly promise that: All the quotes are only for learning and communication, If there is infringement, I will delete them immediately.