TL
TL;DR
By introducing several improvements to the AlphaZero process and architecture, this work greatly accelerate self-play learning in Go, achieving a 50x reduction in computation over comparable methods.
Abstract
By introducing several improvements to the AlphaZero process and architecture, we greatly accelerate self-play learning in Go, achieving a 50x reduction in computation over comparable methods. Like AlphaZero and replications such as ELF OpenGo and Leela Zero, our bot KataGo only learns from neural-net-guided Monte Carlo tree search self-play. But whereas AlphaZero required thousands of TPUs over several days and ELF required thousands of GPUs over two weeks, KataGo surpasses ELF's final model after only 19 days on fewer than 30 GPUs. Much of the speedup involves non-domain-specific improvements that might directly transfer to other problems. Further gains from domain-specific techniques reveal the remaining efficiency gap between the best methods and purely general methods such as AlphaZero. Our work is a step towards making learning in state spaces as large as Go possible without large-scale computational resources.
References26 items
1
SAI: a Sensible Artificial Intelligence that plays with handicap and targets high scores in 9x9 Go (extended version)
2
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
3
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
4
SAI a Sensible Artificial Intelligence that plays Go
5