More actions
imported>rabierre No edit summary |
(Repair MoniWiki formatting after migration) |
||
| (2 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
[[pagelist(^(머신러닝스터디/2017/))]] | |||
* CNN, Artistic style | * CNN, Artistic style | ||
* Reinforcement learning, game play | * Reinforcement learning, game play | ||
| Line 4: | Line 6: | ||
=== 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 ==== | ||
| Line 17: | Line 26: | ||
* model-free | * model-free | ||
* 끌나지 않은 경험에서도 학습 가능하다(Bootstraping) | * 끌나지 않은 경험에서도 학습 가능하다(Bootstraping) | ||
Latest revision as of 14:01, 26 March 2026
[[pagelist(^(머신러닝스터디/2017/))]]
- CNN, Artistic style
- Reinforcement learning, game play
Reinforcement Learning
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
- 직접적인 경험으로부터 배움
- Model-free : 직접적인 MDP transition과 보상을 알 필요가 없다
- 끝난 에피소드로부터 학습한다.
- episodic MDP 문제만 풀 수 있다.
Temporal-Difference Learning
- 경험으로부터 학습한다
- model-free
- 끌나지 않은 경험에서도 학습 가능하다(Bootstraping)