Learning

2026

RL Note 3: Markov Decision Process

Prologue It’s almost been half a year since I first decided to kick off this RL notes series. I apologize for the delay – …
Read more
2025

RL Note 2: Multi-Armed Bandits

Prologue In the last post, we introduced the basics of RL—action, reward, state, value, policy, model, etc.—so you should now have a rough …
Read more

RL Note 1: Basics

Prologue It’s been a while since I last updated this blog, so I’m kicking off a new series.
Read more
2024

高代选讲期末重点整理

此文为宗正宇老师在最后一节课所划六个重点的整理,权作期末预习(x) 求特征多项式和极小多项式 特征多项式 $f(\lambda)=\left|\lambda I-A\right|$
Read more

Chapter2 Using 🤗 Transformers

Behind the pipeline pipeline() groups preprocessing, model inference, and postprocessing together.
Read more

Chapter1 Transformer Models

最近打算入门 NLP,在自学 🤗 的 NLP Course,但是感觉自己过于摆烂了。于是打算边学边做笔记,争取在期末之前把本课程学完 Pipeline the most basic object in the 🤗 Transformers llibrary It can: …
Read more

生成对抗网络

本文是数据科学导论期末大作业展示的报告,拿来随便水一篇博客hh 0 引言 生成对抗网络 (Generative Adversarial Network, GAN) 是一种十分流行的机器学习模型。自2014年Ian Goodfellow等人首次提出以来,GAN迅速在学术界和工业界引 …
Read more