3
$\begingroup$

Google says that their new AI program MuZero learnt the rules of chess and some other board games without being told so. How is this even possible?

https://towardsdatascience.com/deepmind-unveils-muzero-a-new-agent-that-mastered-chess-shogi-atari-and-go-without-knowing-the-d755dc80ff08

Improve this question
$\endgroup$
2
  • 3
    $\begingroup$ Check Appendix A of the original paper, section titled "Actions Available". The rules are actually used at the root of the search tree. But after that, the hidden state is evaluated independent of the rules; the model learns to make legal moves. arxiv.org/pdf/1911.08265.pdf $\endgroup$
    – serali
    Nov 30, 2019 at 12:55
  • 1
    $\begingroup$ Why do you think this is impossible? You could ask the exact same question about any feat of human learning. If you are interested in the specific algorithms that are used, you should clarify in your question. $\endgroup$
    – Mathias Müller
    Jan 28, 2020 at 17:35

0

Reset to default

You must log in to answer this question.

Browse other questions tagged .