SAI: a Sensible Artificial Intelligence that plays with handicap and targets high scores in 9x9 Go (extended version)
This addresses the problem of achieving robust, high-scoring play in Go with handicaps, which is novel but incremental as it builds on existing AlphaGo methods.
The researchers developed a new model for perfect information two-player zero-sum games that targets high scores to achieve perfect play, integrating it into AlphaGo's pipeline to create a superhuman 9x9 Go player that can play with handicaps and minimize suboptimal moves.
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.