Toggle menu
Toggle personal menu
Not logged in
Your IP address will be publicly visible if you make any edits.

데블스캠프2017/강화학습으로컴퓨터에게고전게임플레이시키기: Difference between revisions

From ZeroWiki
No edit summary
No edit summary
Line 1: Line 1:
= machine learning =
= machine learning =


* supervised learning
== supervised learning ==
* unsupervised learning
* 학습을 시킬 때 label에 정답이 있는 것
* reinforcement learning
* Need input, target
temp
* Learning from difference between prediction and target
* e.g. mnist, classification
 
== unsupervised learning ==
* label 이 미리 정해져 있지 않은 것
* Need input
* Cluster by distance between inputs
* Can't predict outcome
* e.g. clustering
== reinforcement learning ==
* 일종의 unsupervised learning
* input : environment, reward, output : action
* Learn from try
* Model free
* e.g. game play, stock trading
== reinforcement learning ==
* Q learning
* Neural Network
* DQN : Deep Q Learning
== Basic knowledge
* MDP : Markov Decision Process
* Bellman equation
* Dynamic programming
* Value, Polish
* Value function, Polish function
* Value iteration, Polish iteration
 
==



Revision as of 03:28, 1 July 2017

machine learning

supervised learning

  • 학습을 시킬 때 label에 정답이 있는 것
  • Need input, target
  • Learning from difference between prediction and target
  • e.g. mnist, classification

unsupervised learning

  • label 이 미리 정해져 있지 않은 것
  • Need input
  • Cluster by distance between inputs
  • Can't predict outcome
  • e.g. clustering

reinforcement learning

  • 일종의 unsupervised learning
  • input : environment, reward, output : action
  • Learn from try
  • Model free
  • e.g. game play, stock trading

reinforcement learning

  • Q learning
  • Neural Network
  • DQN : Deep Q Learning

== Basic knowledge

  • MDP : Markov Decision Process
  • Bellman equation
  • Dynamic programming
  • Value, Polish
  • Value function, Polish function
  • Value iteration, Polish iteration

==