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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We study Monte Carlo tree search (MCTS) in zero-sum extensive-form games withperfect information and simultaneous moves. We present a general template ofMCTS algorithms for these games, which can be instantiated by various selectionmethods. We formally prove that if a selection method is $\epsilon$-Hannanconsistent in a matrix game and satisfies additional requirements onexploration, then the MCTS algorithm eventually converges to an approximateNash equilibrium (NE) of the extensive-form game. We empirically evaluate thisclaim using regret matching and Exp3 as the selection methods on randomlygenerated games and empirically selected worst case games. We confirm theformal result and show that additional MCTS variants also converge toapproximate NE on the evaluated games.

Convergence of Monte Carlo Tree Search in Simultaneous Move Games