機器學習增強學習工程要點【待完成】

原創 tangwing 2020-04-27 11:02

TensorFlow

  1. 主要concept是首先定義好tensor計算網絡，包括各個node涉及的操作等等。需要讀取值的時候使用session.run發起計算。有些lambda的感覺。爲了調試方面，也有eager模式，運算立即執行。
  2. 涉及到Neural Network可以使用TF中Keras，更加方便而且API比較穩定。
  3. 注意TF2.0版本與之前的區別

Gym

  1. OpenAI的Gym可以方便地進行RL實驗，也可以註冊自己的environement

 

發表評論
所有評論
還沒有人評論，想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章

A Road Map for Deep Learning

點這個： https://towardsdatascience.com/a-road-map-for-deep-learning-b9aee0b2919f

tangwing 2020-07-08 12:17:01

Stochastic Optimization: Casual Notes

Currently learning stochastic optimization (SO) theory, I will note important content here. Some book references ar

tangwing 2020-07-08 12:17:01

Graph Neural Network: A First Glance

@[TOC]GNN Resources 從圖(Graph)到圖卷積(Graph Convolution)：漫談圖神經網絡模型 (一) Vocabulary Fixed Point Theorem : a convergency

tangwing 2020-07-08 12:17:01

[NOTE in progress] ECE236C - Optimization Methods for Large-Scale Systems [on going]

Source:http://www.seas.ucla.edu/~vandenbe/ee236c.html   Introduction Outline First-order algorithms Decomposition and s

tangwing 2020-07-08 12:16:49

An Overview of Reinforcement Learning

強化學習概覽 This overview is largely based on this article: https://medium.com/@SmartLabAI/reinforcement-learning-algorithms

tangwing 2020-07-08 12:16:49

【轉】MCMC採樣詳解

Check here:https://zhuanlan.zhihu.com/p/37121528

tangwing 2020-07-08 12:16:49

Taylor, Jacobian, Hessian, Newton and all the else about gradient

tangwing 2020-05-04 16:35:01

Brief Intro of Deep Learning【李宏毅課程筆記-待完成】

tangwing 2020-04-27 11:02:12

RL by Tsitsiklis 【Notes待完成】

tangwing 2020-04-27 11:02:12

Machine Learning Notes [更新中]

tangwing 2020-04-27 11:02:12

A Road Map for Deep Learning

點這個： https://towardsdatascience.com/a-road-map-for-deep-learning-b9aee0b2919f

tangwing 2020-07-08 12:17:01

Stochastic Optimization: Casual Notes

Currently learning stochastic optimization (SO) theory, I will note important content here. Some book references ar

tangwing 2020-07-08 12:17:01

Graph Neural Network: A First Glance

@[TOC]GNN Resources 從圖(Graph)到圖卷積(Graph Convolution)：漫談圖神經網絡模型 (一) Vocabulary Fixed Point Theorem : a convergency

tangwing 2020-07-08 12:17:01

[NOTE in progress] ECE236C - Optimization Methods for Large-Scale Systems [on going]

Source:http://www.seas.ucla.edu/~vandenbe/ee236c.html   Introduction Outline First-order algorithms Decomposition and s

tangwing 2020-07-08 12:16:49

An Overview of Reinforcement Learning

強化學習概覽 This overview is largely based on this article: https://medium.com/@SmartLabAI/reinforcement-learning-algorithms

tangwing 2020-07-08 12:16:49