Načítá se...

Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data

Deep neural networks have been successfully applied in learning the board games Go, chess, and shogi without prior knowledge by making use of reinforcement learning. Although starting from zero knowledge has been shown to yield impressive results, it is associated with high computationally costs esp...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Front Artif Intell
Hlavní autoři: Czech, Johannes, Willig, Moritz, Beyer, Alena, Kersting, Kristian, Fürnkranz, Johannes
Médium: Artigo
Jazyk:Inglês
Vydáno: Frontiers Media S.A. 2020
Témata:
On-line přístup:https://ncbi.nlm.nih.gov/pmc/articles/PMC7861260/
https://ncbi.nlm.nih.gov/pubmed/33733143
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3389/frai.2020.00024
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!