DeepAI AI Chat
Log In Sign Up

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

by   Francesco Morandin, et al.

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. 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.


page 1

page 2

page 3

page 4


Monte Carlo Tree Search for a single target search game on a 2-D lattice

Monte Carlo Tree Search (MCTS) is a branch of stochastic modeling that u...

Zero-Sum Two Person Perfect Information Semi-Markov Games: A Reduction

Look at the play of a Perfect Information Semi-Markov game (PISMG). As t...

Leela Zero Score: a Study of a Score-based AlphaGo Zero

AlphaGo, AlphaGo Zero, and all of their derivatives can play with superh...

Multiplayer AlphaZero

The AlphaZero algorithm has achieved superhuman performance in two-playe...

Random perfect information games

The paper proposes a natural measure space of zero-sum perfect informati...

The αμ Search Algorithm for the Game of Bridge

αμ is an anytime heuristic search algorithm for incomplete information g...

Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration

Expert Iteration (ExIt) is an effective framework for learning game-play...