HackerPapers

arXiv:1509.01549cs.AI

Giraffe: Using Deep Reinforcement Learning to Play Chess

Matthew Lai

Abstract

This report presents Giraffe, a chess engine that uses self-play to discover all its domain-specific knowledge, with minimal hand-crafted knowledge given by the programmer. Unlike previous attempts using machine learning only to perform parameter-tuning on hand-crafted evaluation functions, Giraffe's learning system also performs automatic feature extraction and pattern recognition. The trained evaluation function performs comparably to the evaluation functions of state-of-the-art chess engines - all of which containing thousands of lines of carefully hand-crafted pattern recognizers, tuned over many years by both computer chess experts and human chess masters. Giraffe is the most successful attempt thus far at using end-to-end machine learning to play chess.

arXiv comments
MSc Dissertation
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence cs.LGMachine Learning cs.NENeural and Evolutionary Computing

On Hacker News

Linked by 9 identifiable commenters in 9 comments across 9 threads, from Sep 2015 to Dec 2017. Found in 3 HN submissions from Sep 2015 to Sep 2015. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments9 threads

  1. Mastering Chess and Shogi by Self-Play with General Reinforcement Learning 1 comment

    • It's certainly not the first NN chess program. You may remember one of OP author's Giraffe NN (https://arxiv.org/abs/1509.01549) which was essentially 'AlphaGo for chess'. But like the original AG, it struggles to learn and Lai had a lot less computation as a student than he…

      gwernView on HNParent context

  2. AI Uses Less Than Two Minutes of Videogame Footage to Recreate Game Engine 1 comment

    • > They're useless to you because you don't seem to understand how neural network or current AI tech works. In the current fashion, generalist AI like a game engine is very much impossible. I have some understanding how that works. You seem to read me incorrectly and extend what…

      kyberiasView on HNParent context

  3. Alpha Go Zero: How and Why It Works 1 comment

    • There was a project for chess, called giraffe https://bitbucket.org/waterreaction/giraffe whose author shut it down after joining google deep mind: http://www.talkchess.com/forum/viewtopic.php?t=59003 He thinks it's only a matter of time till machine learning beats hand crafted…

      naveen99View on HNParent context

  4. AlphaGo Zero: Learning from scratch 1 comment

    • I didn't see the talk, but I'm guessing he was referring to the Giraffe engine done by Matthew Lai (https://arxiv.org/abs/1509.01549). The main thing there is that he only learns an evaluation function, not a policy. Giraffe still uses classical alpha-beta search over the full…

      shmageggyView on HNParent context

  5. Spawkfish: Neural network chess 1 comment

    • Seems very interesting, I really think these approaches will work rather well on a variety of games. Very exciting times. Btw, there is another already Open Source Neural Network Chess engine that might be worth exploring for similar ideas. That codebase already has a minmax…

      jhartmannView on HNParent context

  6. In just 72 hours a deep learning engine has learned chess to Master level 1 comment

    • Discussion? https://news.ycombinator.com/item?id=10216710 : 2 comments https://news.ycombinator.com/item?id=10230201 : 1 comment https://news.ycombinator.com/item?id=10216715 : 1 comment https://news.ycombinator.com/item?id=10219759 : 2 comments ======== Full summary…

      ColinWrightView on HNParent context

  7. Artificial General Intelligence via the CogPrime Architecture (2012) [pdf] 1 comment

    • Probably this: http://www.technologyreview.com/view/541276/deep-learning-ma... http://arxiv.org/abs/1509.01549

      cjauvinView on HNParent context

  8. Deep Learning Machine Teaches Itself International Master Level Chess in 72 HRs 1 comment

    • Interestingly, the neural net used is not really that deep: it has only two hidden layers (see figure 3 in the paper[1]). The innovations are really in how the researcher is representing inputs using different "modalities" (see section 4.1 "Feature Representation"), generating a…

      cs702View on HNParent context

  9. Giraffe: Using Deep Reinforcement Learning to Play Chess 1 comment

Submitted to Hacker News

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