Accelerating Self-Play Learning in Go
share
By introducing several new Go-specific and non-Go-specific techniques along with other tuning, we accelerate self-play learning in Go. Like AlphaZero and Leela Zero, a popular open-source distributed project based on AlphaZero, our bot KataGo only learns from neural net Monte-Carlo tree-search self-play. With our techniques, in only a week with several dozen GPUs it achieves a likely strong pro or perhaps just-super-human level of strength. Compared to Leela Zero, we estimate a roughly 5x reduction in self-play computation required to achieve that level of strength, as well as a 30x to 100x reduction for reaching moderate to strong amateur levels. Although we so far have not tested in longer runs, we believe that our techniques hold promise for future research.
READ FULL TEXT