*RL
-
-
-
MuZero: Mastering Go, chess, shogi and Atari without rules*RL/RL_DeepMind 2025. 11. 12. 22:45
DeepMind 너무 멋있어요 ♡ https://deepmind.google/blog/muzero-mastering-go-chess-shogi-and-atari-without-rules/ MuZero: Mastering Go, chess, shogi and Atari without rulesIn 2016, we introduced AlphaGo, the first artificial intelligence (AI) program to defeat humans at the ancient game of Go. Two years later, its successor - AlphaZero - learned from scratch to master …deepmind.google In 2016, we introdu..
-
시험 공부*RL/IIT6051 2025. 10. 19. 23:28
부실하게 한 거 같다.어떡하지? 어제 lecture note (slide) 한번 다 훑고,오늘은 kaist online 강좌 RL 1 정주행했다. 딱 이틀 셤 공부라니.. ㄷㄷㄷ 너무 부실한데..? 그간 RL 공부를 나름 하고, 논문도 나름 읽었지만시험을 잘 볼 자신은 없다. ㅎㅎ(이게 뭔 궤변이람. 변명이라면, paper와 수업시간에 배우는 classic RL과 괴리가 좀 있다.중간고사 이후부터 좀 더 재밌어질 거 같다.) 뜻밖의 소득은,kaist online RL 강좌가 엄청난 quality라는 것!!!!신하용교수님. 엄청 잘 가르쳐주신다. 셤 끝나고 나면, RL 2도 정주행해야겠다.너무 재밌게 꼼꼼히 잘 가르쳐주신다.교수님, 감사합니다 ♡
-
HW 2 - Random Walk TD(0) & MC value estimation*RL/IIT6051 2025. 9. 30. 09:13
code: https://github.com/letter-night/RL_IIT6051/blob/main/HW_2.ipynb RL_IIT6051/HW_2.ipynb at main · letter-night/RL_IIT6051Reinforcement Learning Class Materials. Contribute to letter-night/RL_IIT6051 development by creating an account on GitHub.github.com
-
HW 1 - value evaluation*RL/IIT6051 2025. 9. 16. 20:59
Code: https://github.com/letter-night/RL_IIT6051/blob/main/HW_1.ipynb RL_IIT6051/HW_1.ipynb at main · letter-night/RL_IIT6051Reinforcement Learning Class Materials. Contribute to letter-night/RL_IIT6051 development by creating an account on GitHub.github.com
-