AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong

In recent years, deep neural networks for strategy games have made significant progress. AlphaZero-like frameworks which combine Monte-Carlo tree search with reinforcement learning have been successfully applied to numerous games with perfect information. However, they have not been developed for do...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awduron:	Jannis Blüml, Johannes Czech, Kristian Kersting
Fformat:	Artigo
Iaith:	Inglês
Cyhoeddwyd:	Frontiers Media S.A. 2023-05-01
Cyfres:	Frontiers in Artificial Intelligence
Pynciau:	imperfect information games deep neural networks reinforcement learning AlphaZero Monte-Carlo tree search perfect information Monte-Carlo
Mynediad Ar-lein:	https://www.frontiersin.org/articles/10.3389/frai.2023.1014561/full
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!