Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 16 - Monte Carlo Tree Search

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/ai Professor Emma Brunskill, Stanford University http://onlinehub.stanford.edu/ Professor Emma Brunskill Assistant Professor, Computer Science Stanford AI for Human Impact Lab Stanford Artificial Intelligence Lab Statistical Machine Learning Group To follow along with the course schedule and syllabus, visit: http://web.stanford.edu/class/cs234/i... 0:00 Introduction 0:58 Class Structure 1:26 Monte Carlo Tree Search 3:42 Model-Based Reinforcement Learning 4:19 Model-Based and Model-Free RL 7:04 Advantages of Model-Based RL 10:57 MDP Model Refresher 13:11 Table Lookup Model 20:00 Sample-Based Planning 21:11 Back to the AB Example 38:46 Simple Monte-Carlo Search 42:20 Monte-Carlo Tree Search (MCTS) 48:48 Upper Confidence Tree (UCT) Search 52:43 Case Study the Game of Go 54:46 Applying Monte-Carlo Tree Search (1) 56:14 Applying Monte-Carlo Tree Search (5)