from Hacker News

Playing hard exploration games by watching YouTube

by indescions_2018 on 5/30/18, 12:17 PM with 11 comments

  • by sleepychu on 5/30/18, 12:54 PM

    Neat, I don't understand what they mean by having embedded a reward video into the set. Is that a video where copying the behaviour will deliver victory?
  • by eric_h on 5/30/18, 4:39 PM

    here's video of the agent actually playing (linked in the paper): https://www.youtube.com/watch?v=Msy82sIfprI
  • by jexah on 5/30/18, 1:14 PM

    This is really cool. A step in the right direction towards general learning through observation.
  • by erikb on 5/30/18, 4:30 PM

    This is actually quite human. I also watch Let's plays if I struggle with a quest (or game in general).

    Also interesting assumption to say "harder = fewer rewards". Probably doesn't always apply but is a good generalization.

  • by jonbaer on 5/30/18, 1:35 PM

    Are audio cues also analyzed here? ie: "We observe that use of the audio signal in CMC results in more emphasis being placed on key items and their location in the inventory"
  • by navaati on 5/30/18, 12:55 PM

    This should probably say "ML" or "AI" or whatever, I was slightly disappointed to realize it was not a funny paper about… I don't know to be fair.