Cargando…
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...
| Autores principales: | , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Frontiers Media S.A.
2023
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10213697/ https://www.ncbi.nlm.nih.gov/pubmed/37251273 http://dx.doi.org/10.3389/frai.2023.1014561 |