Multi-Labelled Value Networks for Computer Go

Wu, Ti-Rong; Wu, I‐Chen; Chen, Guan-Wun; Wei, Ting-Han; Lai, Tung-Yi; Wu, Hung-Chun; Lan, Li-Cheng

doi:10.48550/arxiv.1705.10701

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2019

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these attempts don't use any of the modern Deep RL techniques, and thus their accuracy is quite low. In the more recent paper [17], a Deep CNN is used to predict the final score and 41 different winrates, corresponding to 41 different scores handicap {−20, −19, . .…”

Section: Introductionmentioning

confidence: 99%

SAI: a Sensible Artificial Intelligence that plays with handicap and targets high scores in 9x9 Go (extended version)

Morandin,

Amato,

Fantozzi

et al. 2019

Preprint

View full text Add to dashboard Cite

We develop a new model that can be applied to any perfect information two-player zero-sum game to target a high score, and thus a perfect play. We integrate this model into the Monte Carlo tree search-policy iteration learning pipeline introduced by Google DeepMind with AlphaGo. Training this model on 9×9 Go produces a superhuman Go player, thus proving that it is stable and robust. We show that this model can be used to effectively play with both positional and score handicap. We develop a family of agents that can target high scores against any opponent, and recover from very severe disadvantage against weak opponents. To the best of our knowledge, these are the first effective achievements in this direction.

show abstract

Section: Introductionmentioning

confidence: 99%