Deep-Learning the Hardest Go Problem in the World

Earlier this year, I posted about our project KataGo and research to improve self-play learning in Go, with an initial one-week run showing highly promising results. Several months later in June, KataGo performed a second, longer 19-day run with some major bugfixes and minor optimizations. Starting from scratch and with slightly less hardware than before, up to 28 V100 GPUs, it reached and surpassed the earlier one-week run in barely more than the first three days. By the end of the 19 days, it had reached the strength of ELF OpenGo, Facebook AI Research's multi-thousand-GPU replication of one of AlphaZero's runs - equating to roughly a factor of 50 reduction in computation required. This version of KataGo has also been released to the Go player community for several months now.