SAI a Sensible Artificial Intelligence that plays Go

@article{Morandin2019SAIAS,
  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={2019 International Joint Conference on Neural Networks (IJCNN)},
  year={2019},
  pages={1-8}
}
  • Francesco Morandin, Gianluca Amato, +3 authors Gian-Carlo Pascutto
  • Published 2019
  • Computer Science
  • 2019 International Joint Conference on Neural Networks (IJCNN)
  • 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, hence the winrate for all komi values is obtained, at the price of predicting just one more variable. A second novel feature is that training is based on self-play games that occasionaly branch –with changed komi– when the position is uneven. With this setting, reinforcement learning is shown to work on 7×7 Go, obtaining very… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 15 REFERENCES

    Multilabeled Value Networks for Computer Go

    VIEW 1 EXCERPT

    AlphaSeq: Sequence Discovery with Deep Reinforcement Learning

    • Y. Shao, S. Liew, T. Wang
    • Mathematics, Medicine, Computer Science
    • IEEE transactions on neural networks and learning systems
    • 2019