most citedSAI, a Sensible Artificial Intelligence that plays Go

16 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2022★ 8 cited

Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?

Luca Pasqualini, Gianluca Amato, Marco Fantozzi +5

In the last years, the DeepMind algorithm AlphaZero has become the state of the art to efficiently tackle perfect information two-player zero-sum games with a win/lose outcome. How…

cs.AI2018★ 16 cited

SAI, a Sensible Artificial Intelligence that plays Go

Francesco Morandin, Gianluca Amato, Rosa Gini +3

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 th…