English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The combination of multi-armed bandit (MAB) algorithms with Monte-Carlo treesearch (MCTS) has made a significant impact in various research fields. The UCTalgorithm, which combines the UCB bandit algorithm with MCTS, is a good exampleof the success of this combination. The recent breakthrough made by AlphaGo,which incorporates convolutional neural networks with bandit algorithms inMCTS, also highlights the necessity of bandit algorithms in MCTS. However,despite the various investigations carried out on MCTS, nearly all of themstill follow the paradigm of treating every node as an independent instance ofthe MAB problem, and applying the same bandit algorithm and heuristics on everynode. As a result, this paradigm may leave some properties of the game treeunexploited. In this work, we propose that max nodes and min nodes havedifferent concerns regarding their value estimation, and different banditalgorithms should be applied accordingly. We develop the Asymmetric-MCTSalgorithm, which is an MCTS variant that applies a simple regret algorithm onmax nodes, and the UCB algorithm on min nodes. We will demonstrate theperformance of the Asymmetric-MCTS algorithm on the game of $9\times 9$ Go,$9\times 9$ NoGo, and Othello.

Asymmetric Move Selection Strategies in Monte-Carlo Tree Search: Minimizing the Simple Regret at Max Nodes