English

SAI, a Sensible Artificial Intelligence that plays Go

Artificial Intelligence 2019-11-28 v2

Abstract

We propose a multiple-komi modification of the AlphaGo Zero/Leela Zero paradigm. The winrate as a function of the komi is modeled with a two-parameters sigmoid function, so that the neural network must predict just one more variable to assess the winrate for all komi values. A second novel feature is that training is based on self-play games that occasionally branch -- with changed komi -- when the position is uneven. With this setting, reinforcement learning is showed to work on 7x7 Go, obtaining very strong playing agents. As a useful byproduct, the sigmoid parameters given by the network allow to estimate the score difference on the board, and to evaluate how much the game is decided.

Keywords

Cite

@article{arxiv.1809.03928,
  title  = {SAI, a Sensible Artificial Intelligence that plays Go},
  author = {Francesco Morandin and Gianluca Amato and Rosa Gini and Carlo Metta and Maurizio Parton and Gian-Carlo Pascutto},
  journal= {arXiv preprint arXiv:1809.03928},
  year   = {2019}
}

Comments

Updated for IJCNN 2019 conference

R2 v1 2026-06-23T04:02:29.860Z