Go to login Go to sub menu Go to text

Login / Sign Up

강화학습 1

KAIST 산업및시스템공학과 신하용 교수님

Copy URL BAND Facebook Twitter

강화학습 1

강화학습 1

http://kooc.kaist.ac.kr/reinforcement

Thumb up 49 Learner 182

Sub menu

강의
1. 강화학습이란?
2. 강화학습의 특징과 사례
3. 동적 시스템
4. 강화학습 구성요소
5. Quiz 1
1. Markov Chain
2. Markov Reward Process
3. Markov Decision Process
4. Quiz 2
1. Dynamic programming?
2. Policy evaluation
3. Optimal policy
4. Asynchronous DP
5. Quiz 3
1. Monte Carlo method 개요
2. Stochastic approximation
3. MC policy evaluation
4. MC control
5. Quiz 4
1. TD learning 개요
2. TD control
3. Q learning
4. Double Q learning
5. Quiz 5
1. n-step return
2. TD(λ) policy evaluation
3. Eligibility trace와 TD control
4. Q(λ) algorithm
5. Quiz 6
1. Value function approximation 개요
2. Features for VFA
3. Application of VFA : Cartpole
4. Linear VFA for Cartpole
5. Quiz 7
토론

Reverse sort

Please typing a title.

강의 Help

1. Introduction

강의시간43:54
2. Markov Decision Process

강의시간34:44
3. Dynamic Programming

강의시간46:48
4. Monte Carlo methods

강의시간01:06:02
5. Temporal difference methods

강의시간57:15
6. n-Step TD methods

강의시간49:52
7. Value function approximation

강의시간53:02

Coming soon.

이 사이트는 edwith의 온라인강좌 플랫폼을 사용하고 있습니다. 지식나눔과 배움의 기회에 참여하세요. Powered by