style(hus): polish readme (opendilab#182)

README.md

@@ -6,7 +6,7 @@ Get started at
 [English Docs](https://di-engine-docs.readthedocs.io/en/latest/index.html) | 
 [中文文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/index.html)
 
-This is an educational resource produced by OpenDILab that makes it easier to learn about Decision Intelligence and DI-engine
+This is an educational resource produced by OpenDILab that makes it easier to learn about Decision Intelligence and DI-engine.
 
 For the unfamiliar: [Decision Intelligence](https://en.wikipedia.org/wiki/Decision_intelligence#Relationship_to_artificial_intelligence_and_machine_learning) is an engineering discipline that augments data science with theory from social science, decision theory, and managerial science.
 
@@ -15,7 +15,7 @@ This documentation contains a variety of helpful resources, including:
 - an [introduction](https://di-engine-docs.readthedocs.io/en/latest/00_intro/index.html) about DI-engine | [DI-engine 介绍](https://di-engine-docs.readthedocs.io/zh_CN/latest/00_intro/index_zh.html)
 - an [essay](https://di-engine-docs.readthedocs.io/en/latest/10_concepts/basic_rl.html) about  important Concepts of reinforcement learning ｜ [强化学习重要概念](https://di-engine-docs.readthedocs.io/zh_CN/latest/10_concepts/basic_rl_zh.html)
 - a [classification ](https://di-engine-docs.readthedocs.io/en/latest/02_algo/index.html) of reinforcement learning algorithms |  [强化学习算法分类](https://di-engine-docs.readthedocs.io/zh_CN/latest/02_algo/index_zh.html)
-- a [curated list](https://di-engine-docs.readthedocs.io/en/latest/12_policies/index.html) of reinforcement algorithms cheat sheet organized by learning methods ｜ [DI-engine实现的强化学习算法](https://di-engine-docs.readthedocs.io/zh_CN/latest/12_policies/index_zh.html)
+- a [curated list](https://di-engine-docs.readthedocs.io/en/latest/12_policies/index.html) of reinforcement learning algorithms cheat sheet organized by learning methods ｜ [DI-engine实现的强化学习算法](https://di-engine-docs.readthedocs.io/zh_CN/latest/12_policies/index_zh.html)
 - an [environment example](https://di-engine-docs.readthedocs.io/en/latest/13_envs/index.html) often used by reinforcement learning algorithm ｜ [强化学习算法常用环境示例](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/index_zh.html) 
 - a [series of tutorials ](https://di-engine-docs.readthedocs.io/en/latest/04_best_practice/index.html)on how to migrate your own environment to DI-engine ｜ [如何将自己的环境迁移到DI-engine](https://di-engine-docs.readthedocs.io/en/latest/04_best_practice/index.html)
 -  some [API documentation](https://di-engine-docs.readthedocs.io/en/latest/05_api_doc/index.html) to serve as warm-ups ｜ [API 文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/05_api_doc/index.html)