More actions
No edit summary |
imported>rabierre No edit summary |
||
| Line 3: | Line 3: | ||
=== Reinforcement Learning === | === Reinforcement Learning === | ||
https://en.wikipedia.org/wiki/Bellman_equation | |||
==== Monte-Carlo Reinforcement Learning ==== | ==== Monte-Carlo Reinforcement Learning ==== | ||
Revision as of 07:34, 22 July 2017
- CNN, Artistic style
- Reinforcement learning, game play
Reinforcement Learning
https://en.wikipedia.org/wiki/Bellman_equation
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)