hackertube.io

Deepmind artificial intelligence @ FDOT14

Elizr · demo · Watch on YouTube

What it is

A short smartphone-recorded clip from a 2014 event in Paris where DeepMind CEO Demis Hassabis presents an AI learning to play old Atari games. The system learns from only the video signal and the score. Audio quality is poor.

Why Hacker News recommends it

HN commenters use it as the canonical demo of deep reinforcement learning, noting that watching it teaches more than an article does.

  • 2 people recommended it
  • 3 different months
  • 1 strong recommendations
  • first 2014, last 2016

What HN commenters said

  1. “If you haven't seen the video it's remarkable”

    DeepMind Atari player demo, with tiny source code

    paulsutter, 2016-03 · Strong recommendation · in “Ask HN: What are some examples of beautiful software?”

  2. “you learn more about the tech from a youtube video than from an article”

    DeepMind demo learning games from only the video signal

    mturmon, 2014-12 · Recommendation · in “Google's Intelligence Designer”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: deepmind, atari, demis hassabis, dqn, reinforcement learning

Also recommended by the same people