This AI Does Nothing In Games…And Still Wins!

Share
Embed
  • Published on May 8, 2020
  • ❤️ Check out Weights & Biases and sign up for a free demo here: www.wandb.com/papers
    Their instrumentation for this paper is available here:
    app.wandb.ai/stacey/aprl/repo...
    📝 The paper "Adversarial Policies" is available here:
    adversarialpolicies.github.io
    🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
    Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Daniel Hasegan, Eric Haddad, Eric Martel, Javier Bustamante, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Michael Albrecht, Nader S., Owen Campbell-Moore, Owen Skarpness, Rob Rowe, Robin Graham, Steef, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh
    More info if you would like to appear here: www.patreon.com/TwoMinutePapers
    Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: discordapp.com/invite/hbcTJu2
    Károly Zsolnai-Fehér's links:
    Instagram: twominutepa...
    Twitter: twominutepapers
    Web: cg.tuwien.ac.at/~zsolnai/

Comments • 2 063

  • Game Maker's Toolkit
    Game Maker's Toolkit 2 years ago +8

    Luigi was ahead of his time

  • morn1415
    morn1415 2 years ago +3

    Neo: What are you trying to tell me, that I can dodge bullets?

  • Unkars Thug
    Unkars Thug Year ago +979

    You know, this is basically just an AI learning psychological warfare.

  • Finn Shadow
    Finn Shadow Year ago +429

    I once heard a quote "The best swordsman does not fear the second best swordsman; he fears the worst, for he cannot predict what the worst swordsman will do"

  • Oscar Shanagher
    Oscar Shanagher Year ago +1

    AI: does nothing

  • shantih19
    shantih19 Year ago +522

    This proves that curling into a ball and crying really is the best strategy

  • broncokonco
    broncokonco Year ago +1

    If you look really closely, the blue guy is actually laughing so hard he can’t run straight.

  • Autonomous
    Autonomous 2 years ago +3

    Makes sense. If I saw someone's body collapse in on itself, I'd probably go into shock as well.

  • Dave Langers
    Dave Langers 2 years ago +354

    These off-distribution activations remind me of a chess player playing an unusual opening to get a skilled opponent out of book in order to win more easily.

  • Mike Olson
    Mike Olson Year ago +223

    Imagine playing a game of chess against Deep Blue, and you put your Pawns in a certain way, and Deep Blue just has a f*cking stroke and gives you its Queen.

  • Generic Profile
    Generic Profile 2 years ago +550

    AI:

  • уронить
    уронить Year ago +53

    The AI has such a high confidence value when you change such a little detail because it’s trained to be confident even when it’s real confidence value shouldn’t be that high. That’s the side effect of training an AI by rewarding it for providing conclusive answers when it is correct.

  • Cromptank
    Cromptank 2 years ago +34

    The AI’s are tapping into the raw power of beginner’s luck

  • Wes
    Wes Year ago +6

    I took away two things: 1) The red AI learned to exploit a weakness in the blue AI; and (2) pitting AIs against each other does not produce the best learning.

  • danielhakushi
    danielhakushi Year ago +421

    Terminator: "Sarah Conner?"

  • AdianAntilles

    I have another explanation for the phenomenon. Here, we see a regular tackle attempt by the red figure, and the blue figure anticipates the contact, leaning into a unstable moving position forward, which leads to be problematic if there is no contact at all. I would suspect that the blue figure gets more yards in the non-contact events than it would have when given contact.

  • Curiov
    Curiov 2 years ago +8

    This reminds me when I was much younger and was playing Battle for Middle Earth online 1v1 matches. I was following the best practices found online and thus I was able to identify enemy strategies and counter them, but so did they, as they were following the same best strategies. Basically both the opponent and I were 'trained' to behave based on the inputs we were seeing.

  • TestTest estTest
    TestTest estTest Year ago +5

    This is my fourth or fifth video from you about AI - so combined it's about 30 minutes, and you achieved what a whole semester of studying this topic at the university couldn't: i've become interested in AI. Congratulations.

  • Js Nam
    Js Nam 2 years ago +2

    "The greatest victory is that which requires no battle."

  • aweslayne
    aweslayne 2 years ago +242

    Red: collapses