We develop a new framework for the game of Go to target a high score, and thus a perfect play. We integrate this framework into the Monte Carlo tree search - policy iteration learning pipeline introduced by Google DeepMind with AlphaGo. Training on 9×9 Go produces a superhuman Go player, thus proving that this framework is stable and robust. We show that this player can be used to effectively play with both positional and score handicap. We develop a family of agents that can target high scores against any opponent, recover from very severe disadvantage against weak opponents, and avoid suboptimal moves.
SAI: A sensible artificial intelligence that plays with handicap and targets high scores in 9
Morandin F.;Fantozzi M.;Gini R.;Metta C.;
2020-01-01
Abstract
We develop a new framework for the game of Go to target a high score, and thus a perfect play. We integrate this framework into the Monte Carlo tree search - policy iteration learning pipeline introduced by Google DeepMind with AlphaGo. Training on 9×9 Go produces a superhuman Go player, thus proving that this framework is stable and robust. We show that this player can be used to effectively play with both positional and score handicap. We develop a family of agents that can target high scores against any opponent, recover from very severe disadvantage against weak opponents, and avoid suboptimal moves.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
