Post

[Artificial Intelligence] 04. Search (4): MDPs(Markov Decision Processes)

비결정론적 게임을 가정하고, 상대 에이전트에 대한 불확실성을 기대하는 탐색 알고리즘인 MDPs에 대해 알아봅니다.

Posted
By Youngbeom Cho
views 1 min read

1. Uncertainty & What is MDPs?

2. Components of MDP

3. Policy

4. Discount Factor

5. Value Iteration

Computer Science, RL
adversarial search alpha-beta pruning minimax expectimax
This post is licensed under CC BY 4.0 by the author.