SAI: a Sensible Artificial Intelligence that plays with handicap and targets high scores in 9x9 Go (extended version)

TL;DR

This paper introduces a novel model integrated into Monte Carlo tree search that enables high-score targeting in 9x9 Go, resulting in superhuman play and effective handicap handling, marking a significant advancement in game AI.

Contribution

The paper presents a new model for perfect information two-player zero-sum games that targets high scores, integrated into existing AI frameworks, and demonstrates superhuman performance in 9x9 Go.

Findings

Achieved superhuman performance in 9x9 Go.

Effectively played with handicap and minimized suboptimal moves.

First to develop agents targeting high scores against any opponent.

Abstract

We develop a new model that can be applied to any perfect information two-player zero-sum game to target a high score, and thus a perfect play. We integrate this model into the Monte Carlo tree search-policy iteration learning pipeline introduced by Google DeepMind with AlphaGo. Training this model on 9x9 Go produces a superhuman Go player, thus proving that it is stable and robust. We show that this model can be used to effectively play with both positional and score handicap, and to minimize suboptimal moves. We develop a family of agents that can target high scores against any opponent, and recover from very severe disadvantage against weak opponents. To the best of our knowledge, these are the first effective achievements in this direction.