SAI, a Sensible Artificial Intelligence that plays Go

September 11, 2018 Β· Declared Dead Β· πŸ› IEEE International Joint Conference on Neural Network

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Francesco Morandin, Gianluca Amato, Rosa Gini, Carlo Metta, Maurizio Parton, Gian-Carlo Pascutto arXiv ID 1809.03928 Category cs.AI: Artificial Intelligence Citations 15 Venue IEEE International Joint Conference on Neural Network Last Checked 3 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted