AlphaZero Can Definitely Beat You At Chess, and is Coming to Other Games Soon

Discussion in '[H]ard|OCP Front Page News' started by AlphaAtlas, Dec 7, 2018.

  1. AlphaAtlas

    AlphaAtlas [H]ard|Gawd Staff Member

    Messages:
    1,268
    Joined:
    Mar 3, 2018
    Google's DeepMind has already produced systems that can beat the world's best Go players, as well as systems that can compete with humans in Starcraft II. But according to IEEE Spectrum, DeepMind's AlphaZero system is in a league of its own. AlphaZero can allegedly "crack any game that provides all the information that's relevant to decision-making," given a little bit of time to train. For example, the system taught itself to beat Stockfish, one of the best and most highly developed chess programs in the world, in a mere 24 hours. While the AI has only been trained on Go, Chess and Shogi, the company claims that more complicated games like Poker or even Minecraft are within reach.

    For what it's worth, the system appears to be very good at Go, as it seriously stressed out a high ranking Go player in the video here.

    Poker furnishes a good example of such games of "imperfect" information: Players can hold their cards close to their chests. Other examples include many multiplayer games, such as StarCraft II, Dota, and Minecraft. But they may not pose a worthy challenge for long. "Those multiplayer games are harder than Go, but not that much higher," Campbell tells IEEE Spectrum. "A group has already beaten the best players at Dota 2, though it was a restricted version of the game; Starcraft may be a little harder. I think both games are within 2 to 3 years of solution."
     
  2. Inu

    Inu [H]ard|Gawd

    Messages:
    2,019
    Joined:
    Jun 29, 2004
    Queue obligatory "It became self aware at 4:54 pm" post.
     
    GoldenTiger likes this.
  3. viivo

    viivo Gawd

    Messages:
    864
    Joined:
    Sep 7, 2005
    I hate myself, but can it play Crysis?
     
    trandoanhung1991 and drescherjm like this.
  4. WhoMe

    WhoMe Gawd

    Messages:
    840
    Joined:
    Jan 3, 2018
    While this could lead eventually to better game AI's it can be very frustrating to play against something that always wins. So they need to have ways of introducing mistakes to the AI so it can play at lower levels. I'd much prefer this to the big advantages the AI gets in games like Civilization. Maybe one way to do this is copy the AI at various points in its learning process.
     
    Trixar likes this.
  5. travisty

    travisty Gawd

    Messages:
    731
    Joined:
    Feb 3, 2016
    One possibility is to have multiple states of the AI along its learning. Easy is it learned for a few hours. Medium it learned for ten, impossible it learned for a day.

    I'd like to see how big, memory wise, these AIs get. Do they stay relatively static size wise, linear growth, or exponential?
     
    JoeRChillin likes this.
  6. gtrguy

    gtrguy [H]Lite

    Messages:
    124
    Joined:
    Oct 8, 2009
    "Shall we play a game?"
     
  7. EODetroit

    EODetroit [H]ard|Gawd

    Messages:
    1,453
    Joined:
    Oct 20, 2004
    If it'll play Axis and Allies or Monopoly with me even after it knows its going to lose, I'm all for it.
     
    CVNet1 and clockdogg like this.
  8. Meeho

    Meeho [H]ardness Supreme

    Messages:
    4,178
    Joined:
    Aug 16, 2010
    Yeah, good luck with poker. I doubt there will be an AI capable enough in at least another decade.
     
    Last edited: Dec 7, 2018
  9. SPARTAN VI

    SPARTAN VI [H]ardness Supreme

    Messages:
    6,901
    Joined:
    Jun 12, 2004
    Total War games desperately need this.
     
    Trixar likes this.
  10. clockdogg

    clockdogg Gawd

    Messages:
    722
    Joined:
    Dec 12, 2007
    Here's a high stakes game that would be nice to win - unless the winner has already been selected and we're just watching the replay.
     
  11. BSmith

    BSmith [H]ard|Gawd

    Messages:
    1,285
    Joined:
    Nov 9, 2017
    This is it. The day it happened. The day they gave every machine the ability to learn to KILL US ALL!
     
  12. Krenum

    Krenum [H]ardForum Junkie

    Messages:
    14,617
    Joined:
    Apr 29, 2005
    What about 3D chess?

    hqdefault.jpg
     
    GoldenTiger likes this.
  13. WhoMe

    WhoMe Gawd

    Messages:
    840
    Joined:
    Jan 3, 2018
    That's easy just melt the chess pieces. No good AI should be without that ability.
     
    GoldenTiger likes this.
  14. Master_shake_

    Master_shake_ Little Bitch

    Messages:
    7,076
    Joined:
    Apr 9, 2012
    bet i could take it in a foot race.
     
    Madmeerkat55 likes this.
  15. Vader1975

    Vader1975 Gawd

    Messages:
    720
    Joined:
    May 11, 2016
    "crack any game that provides all the information that's relevant to decision-making,"
    Aka know things that are not displayed to the human player. Like positions of all bases and mines and how much of everything is in them prior to start.
    I call this cheating.
     
  16. dgz

    dgz [H]ardness Supreme

    Messages:
    4,845
    Joined:
    Feb 15, 2010
    Perfect information games are nothing like StarCraft. Blizzard has opened their API more than an year ago and so far no one has shown an AI player that works. I'll give it a few more years.

    How is having a look at the chess board cheating?
     
  17. Vader1975

    Vader1975 Gawd

    Messages:
    720
    Joined:
    May 11, 2016
    Starcraft 2 seeing the whole board and all information about it while Fog of war is still active.