当前位置:网站首页>How to get started quickly and strengthen learning?
How to get started quickly and strengthen learning?
2022-07-27 05:28:00 【Charleslc's blog】
How to get started quickly and strengthen learning ?
Understand the concept of reinforcement learning :
- Books 《Reinforcement Learning-An Introduction》 author :Richard Sutton Read address :http://incompleteideas.net/book/the-book-2nd.html
- David Silver Teaching courses , Video address :http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html
- Pieter Abbeel and John Schulman (Open AI/ Berkeley AI Research Lab). Address :https://people.eecs.berkeley.edu/~pabbeel/nips-tutorial-policy-optimization-Schulman-Abbeel.pdf
- Start testing reinforcement learning projects
- Blog : How to use strategy gradient training ATARI Pong agent Address :https://karpathy.github.io/2016/05/31/rl/
- DeepMind Lab, Open source 3D Game platform , Based on agent Of AI Research creation , Rich simulation environment . DeepMind It is definitely a big guy team in reinforcement learning research , alphago It was invented . Address :https://deepmind.com/blog/open-sourcing-deepmind-lab/
- Project Malmo, An artificial intelligence experimental platform supporting the basic research of artificial intelligence . Address :https://www.microsoft.com/en-us/research/project/project-malmo/
- OpenAI gym, A toolbox for constructing and comparing reinforcement learning algorithms . Address :https://gym.openai.com/
Related:https://www.kdnuggets.com/2018/03/5-things-reinforcement-learning.html
边栏推荐
- Li Hongyi machine learning team learning punch in activity day05 --- skills of network design
- 35. Scroll
- JDBC API details
- mq设置过期时间、优先级、死信队列、延迟队列
- JVM Part 1: memory and garbage collection part 9 - runtime data area - object instantiation, memory layout and access location
- JVM上篇:内存与垃圾回收篇三--运行时数据区-概述及线程
- During its low-level period, this slave edge causes the instruction number to make a corresponding model
- LeetCode之6 ZigZag Conversion
- 用户的管理-限制
- B1024 科学计数法
猜你喜欢

李宏毅机器学习组队学习打卡活动day05---网络设计的技巧

2021 OWASP top 6-10 collection

JVM Part 1: memory and garbage collection part 7 -- runtime data area heap

35. Scroll

如何将Excel表格中的多列内容合并到一列

JDBC API 详解

SQL数据库→约束→设计→多表查询→事务

Bean's life cycle & dependency injection * dependency auto assembly

JVM Part 1: memory and garbage collection part 12 -- stringtable

Li Hongyi machine learning team learning punch in activity day03 --- error and gradient decline
随机推荐
Cenos7更新MariaDB
How to quickly and effectively solve the problem of database connection failure
事务,订单系统添加事务
268.missing number of leetcode
2022 Zhengzhou light industry Freshmen's competition topic - I won't say if I'm killed
BIO、NIO、AIO区别
redis持久化
B1024 scientific counting method
李宏毅机器学习组队学习打卡活动day05---网络设计的技巧
如何快速上手强化学习?
笔记系列之docker安装Postgresql 14
Three waiting methods of selenium and three processing methods of alert pop-up
学生管理系统
2022年郑州轻工业新生赛题目-打死我也不说
实用小工具: Kotlin 代码片段
数据库设计——关系数据理论(超详细)
整合SSM
数据库迁移报错解决
2021 OWASP top 4: unsafe design
JVM Part 1: memory and garbage collection part 7 -- runtime data area heap