HackerPapers

arXiv:1412.6564cs.LG

Move Evaluation in Go Using Deep Convolutional Neural Networks

Chris J. Maddison, Aja Huang, Ilya Sutskever, David Silver

Abstract

The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any search, it beat the traditional search program GnuGo in 97% of games, and matched the performance of a state-of-the-art Monte-Carlo tree search that simulates a million positions per move.

arXiv comments
Minor edits and included captures in Figure 2
Journal reference
DOI
Subjects
cs.LGMachine Learning cs.NENeural and Evolutionary Computing

On Hacker News

Linked by 3 identifiable commenters in 6 comments across 5 threads, from May 2015 to Jan 2016. Found in 1 HN submission from Feb 2015 to Feb 2015. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. Why Go Still Foils the Computers 1 comment

    • I read http://arxiv.org/abs/1412.6564 earlier this year and tldr they trained a deep net bot that managed to hold about 1-2d on KGS. Since there's no searching going on, that's pretty good, though not as good as CrazyStone or other MCTS bots. (I hadn't heard they went from 6d to…

      JachView on HNParent context

  2. Watch an AI bot play Go [video] 1 comment

    • This Facebook Video suggests it has had months of either training or development, which sounds might be it learning by playing, reinforcement learning in this space could be very interesting - more details would be good. The two breakthrough papers using Deep Conv Nets to play…

      deepnetView on HNParent context

  3. How Google Translate squeezes deep learning onto a phone 2 comments

    • Monte Carlo Tree Search ( Random playout ) is currently the best computer strategy for evaluating a Go position. This is likely due to the way Go works , random playout provides a rough estimate of who controls what territory ( this is how Go is scored ). Recently two…

      deepnetView on HNParent context

    • and the follow up from Google's Deepmind group : Move Evaluation in Go Using Deep Convolutional Neural Networks Chris J. Maddison, Aja Huang, Ilya Sutskever, David Silver http://arxiv.org/abs/1412.6564

      deepnetView on HNParent context

  4. 112th KGS Computer Go Tournament 1 comment

    • What I find shocking isn't only the level of play by machines, but also the number of techniques that can be applied to achieve it. Traditionally they were very domain knowledge based and now they tend to be hybrids. This for me really quantified how deep into the age of AI…

      karmakazeView on HNParent context

  5. Show HN: Recurrent neural net plays 'neural slime volleyball' in JavaScript 1 comment

    • *references Teaching Deep Convolutional Neural Networks to Play Go by Clarke & Storkey http://arxiv.org/abs/1412.3409 Move Evaluation in Go Using Deep Convolutional Neural Networks by Maddison , Huang , Silver & Sutskever http://arxiv.org/abs/1412.6564 Tesauro's TD-Gammon…

      deepnetView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.