Edith: the digital twin in healthcare
A digital twin in healthcare is a model of a person's systems with its specific parameters... with many very practical applications
Publish at October 16 2024 Updated October 16 2024
When an A.I. tackles a game like chess or Go, it has access to the same information as its opponent, so it can learn relatively quickly; but when it comes to playing against an opponent who has information it doesn't, it has a much harder time determining the optimal solution.
The FAIRPLAY team at the Centre Inria de Saclay has just taken a major step forward. Their feat? Optimizing algorithms capable of developing strategies while playing. Bringing together two researchers from Inria, five from ENSAE and five from Criteo, the team's mission is to study the interactions between game theory, machine learning and economics.
"In the field of games, the best algorithm is the one that will be optimal when faced with the worst possible situation."
It is hoped that they will succeed in determining this algorithm, thereby downgrading all online poker sites. Players will benefit just as much as suppliers.
For the full article: Artificial intelligence, the ultimate poker player
For their research paper:"Local and adaptive mirror descents in extensive-form games".