The authors formally verify several minimax variants with alpha-beta and transposition tables in Dafny, proving one depth-limited negamax variant correct under a new witness-based criterion and exhibiting a counterexample for another.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
Athénan, a minimax-based zero-knowledge RL method without a policy, achieves 296 times lower state-data cost and at least 7 times higher speed than Polygames on multiple games.
citing papers explorer
-
Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.