TechPrufer
Get started
Jane Street
Jane Street logoJane Street · Feature trail

Deep Learning for Go Problem Solving

1 post · Dec 2019

What this trail covers

This post introduces a new capability for applying deep learning techniques to solve complex problems in the game of Go. It details the technical approach of using neural networks to analyze game states and predict optimal moves, aiming to advance AI capabilities in strategic games.

All Jane Street trails
  1. Deep-Learning the Hardest Go Problem in the WorldThis post details the application of deep learning to solve a notoriously difficult Go problem. It describes the architecture of the neural network used, the training process, and the evaluation of its performance against established Go AI benchmarks. The technical contribution lies in demonstrating how deep learning can be effectively applied to complex strategic domains.