| Lecture 1. 오리엔테이션 |
|
수업소개 (Introduction) |
|
00:13:00 |
| Lecture 2. OpenAI GYM 게임 |
|
이론 – Playing OpenAI GYM Games |
|
00:10:00 |
|
실습 – Playing OpenAI GYM Games |
|
00:09:00 |
| Lecture 3: Dummy Q-learning (table) |
|
이론 – Dummy Q-learning (table) |
|
00:21:00 |
|
실습 – Dummy Q-learning (table) |
|
00:13:00 |
| Lecture 4: Q-learning 을 완벽하게 하기 |
|
이론 – Q-learning (table) exploit&exploration and discounted reward |
|
00:17:00 |
|
실습 – Q-learning (table) exploit&exploration and discounted reward |
|
00:07:00 |
| Lecture 05: 비결정론적 환경(non-deterministic world) 에서의 Q-learning |
|
이론 – Q-learning on Nondeterministic Worlds! |
|
00:14:00 |
|
실습 1 – Q-learning on Nondeterministic Worlds! |
|
00:09:00 |
|
실습 1 – Q-learning (Table) Demo by Jae Hyun Lee (배경 음악과 함께) |
|
00:01:00 |
| Lecture 6: Q-Network |
|
이론 – Q-Network |
|
00:17:00 |
|
실습 1 – Q Network for Frozen Lake |
|
00:18:00 |
|
실습 2 – Q Network for Cart Pole |
|
00:22:00 |
| Lecture 7: DQN |
|
이론 – DQN |
|
00:18:00 |
|
실습 1 – DQN 1 (NIPS 2013) |
|
00:19:00 |
|
실습 2 – DQN 2 (Nature 2015) |
|
00:16:00 |
|
실습 3 – DQN Cart Pole Demo (음악 들어 있음)! |
|
00:01:00 |
|
실습 4 – DQN Simple Pacman exercise example (음악과 함께)! |
|
00:01:00 |
