# SAI, a Sensible Artificial Intelligence that plays Go

arXiv: https://arxiv.org/abs/1809.03928 · HTML: https://mlsanity.com/paper/1809.03928/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2018.

## Built on by (most cited first, 5 of 5)

- [Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants](https://mlsanity.com/paper/2102.12375/) (2021)
- [Increasing biases can be more efficient than increasing weights](https://mlsanity.com/paper/2301.00924/) (2023)
- [Spatial State-Action Features for General Games](https://mlsanity.com/paper/2201.06401/) (2022)
- [Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?](https://mlsanity.com/paper/2201.13176/) (2022)
- [A Systematization of the Wagner Framework: Graph Theory Conjectures and Reinforcement Learning](https://mlsanity.com/paper/2406.12667/) (2024)

## Abstract (arXiv)

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.