AlphaJass
Lade...
DOI der Originalpublikation
Zugehörige Forschungsdaten
Projekttyp
angewandte Forschung
Projektbeginn
01.07.2026
Projektende
30.06.2027
Projektstatus
laufend
Projektkontakt
Projektmanager:in
Mitarbeitende
Beschreibung
Zusammenfassung
Although Jass parades as a Swiss card game of national importance, it is in fact a serious problem in game theory, similar to the wire-tap problem. Jass in someways is harder to solve for perfect play than chess or Go, not because of its branching factor, which is relatively small, but because it is a hidden information game where the model has to simulate a complex posterior distribution of 280 billion possible worlds. We are solving this problem using a novel Duel Critique methodology and a multi-phase training scheme involving imitation learning, self-play, and SPARTA, that will eventually distil a super human bot team capable of beating Switzerland’s elite players.
Link
Während FHNW Zugehörigkeit erstellt
Ja
Zukunftsfelder FHNW
Hochschule
Hochschule für Informatik FHNW
Institut
Institut für Data Science
Finanziert durch
Hasler Stiftung
Projektpartner
Jassverband Schweiz (JVS)
Auftraggeberschaft
SAP Referenz
I336-0082-2
Schlagwörter
Jassen
AI
Reinforcement learning
Self-play
Information incomplete
Dual critique
AI
Reinforcement learning
Self-play
Information incomplete
Dual critique