머신러닝스터디/2017 - Revision history

Maintenance script: Repair MoniWiki formatting after migration

2026-03-26T14:01:45Z

Repair MoniWiki formatting after migration

← Older revision		Revision as of 14:01, 26 March 2026
Line 26:		Line 26:
	* model-free		* model-free
	* 끌나지 않은 경험에서도 학습 가능하다(Bootstraping)		* 끌나지 않은 경험에서도 학습 가능하다(Bootstraping)

2017-07-25T15:16:02Z

← Older revision		Revision as of 15:16, 25 July 2017
Line 1:		Line 1:
			[[pagelist(^(머신러닝스터디/2017/))]]

	* CNN, Artistic style		* CNN, Artistic style
	* Reinforcement learning, game play		* Reinforcement learning, game play

2017-07-22T07:57:14Z

← Older revision		Revision as of 07:57, 22 July 2017
Line 4:		Line 4:
	=== Reinforcement Learning ===		=== Reinforcement Learning ===
	https://en.wikipedia.org/wiki/Bellman_equation		https://en.wikipedia.org/wiki/Bellman_equation
			Planning vs Learning
			Planning
			* Know about Model
			* Dynamic Programming
			Learning
			* Model free
			* Monte Carlo method, Temporal Difference learning
	==== Monte-Carlo Reinforcement Learning ====		==== Monte-Carlo Reinforcement Learning ====

2017-07-22T07:34:55Z

← Older revision		Revision as of 07:34, 22 July 2017
Line 3:		Line 3:

	=== Reinforcement Learning ===		=== Reinforcement Learning ===
			https://en.wikipedia.org/wiki/Bellman_equation
	==== Monte-Carlo Reinforcement Learning ====		==== Monte-Carlo Reinforcement Learning ====

2017-07-22T07:11:38Z

← Older revision		Revision as of 07:11, 22 July 2017
Line 13:		Line 13:

	==== Temporal-Difference Learning ====		==== Temporal-Difference Learning ====

			* 경험으로부터 학습한다
			* model-free
			* 끌나지 않은 경험에서도 학습 가능하다(Bootstraping)

2017-07-22T07:08:52Z

← Older revision		Revision as of 07:08, 22 July 2017
Line 5:		Line 5:

	==== Monte-Carlo Reinforcement Learning ====		==== Monte-Carlo Reinforcement Learning ====

			* 직접적인 경험으로부터 배움
			* Model-free : 직접적인 MDP transition과 보상을 알 필요가 없다
			* 끝난 에피소드로부터 학습한다.
			* episodic MDP 문제만 풀 수 있다.


	==== Temporal-Difference Learning ====		==== Temporal-Difference Learning ====

2017-07-22T07:06:23Z

← Older revision		Revision as of 07:06, 22 July 2017
Line 1:		Line 1:
	* CNN, Artistic style		* CNN, Artistic style
	* Reinforcement learning, game play		* Reinforcement learning, game play

			=== Reinforcement Learning ===

			==== Monte-Carlo Reinforcement Learning ====

			==== Temporal-Difference Learning ====

2017-07-22T06:52:10Z

← Older revision	Revision as of 06:52, 22 July 2017
(No difference)

2017-07-22T06:52:03Z

← Older revision		Revision as of 06:52, 22 July 2017
Line 1:		Line 1:
	~~머신러닝스터디/2017의 내용을 써주세요~~		* CNN, Artistic style
			* Reinforcement learning, game play

2017-07-22T06:51:19Z

{CREATE}

New page

머신러닝스터디/2017의 내용을 써주세요