演講公告

時間：104.05.28(四) 10:00-12:00 工程三館 345室

演講者：Prof. Mark Winands

（Department of Knowledge Engineering, Maastricht University, The Netherlands）

演講題目：Minimizing Regret in Monte-Carlo Tree Search

演講摘要：

Regret minimization is important Monte-Carlo Tree Search (MCTS). Recently, simple regret, i.e., the regret of not recommending the best action, has been proposed as an alternative to cumulative regret in MCTS, i.e., regret accumulated over time. Each type of regret is appropriate in different situations. However the majority of MCTS research applies the UCB selection policy for minimizing cumulative regret in the tree. Recently, alternatives such as Sequential Halving have been proposed. In this talk I will discuss how to incorporate the idea of Sequential Halving as a selection policy in MCTS. Results are given for deterministic / stochastic (im)perfect information games.

主持人：吳毅成教授

～歡迎蒞臨聽講！～