Select Page
Poker Forum
Over 1,291,000 Posts!
Poker ForumFTR Community

Alpha Zero vs Stockfish

Results 1 to 14 of 14
  1. #1

    Default Alpha Zero vs Stockfish

    AI just shit the bed.

    https://www.sciencealert.com/it-took...mind-alphazero

    Stockfish is, sorry was, the leading chess computer in the world. It has lots of human input, such as an opening database, strategies, and numerical values assigned to pieces. While Stockfish does recognise that these values are not static, it's weakness appears to be that it does not adjust these values correctly to suit the position.

    Stockfish processes 70,000,000 positions a second.

    Alpha Zero is the games playing baby of Google's Deep Mind. It's just crushed a professional Go player, a world's first, and it was then told the rules of chess and nothing more. No openings, no piece values, just the rules. It began playing itself, and four hours later begain playing Stockfish in a series of 100 games.

    Alpha Zero processes 80,000 a second, while basing its strategy on memory.

    As white, Alpha Zero won 25 and drew 25.
    As black, Alpha Zero won 3 and drew 47.

    Total score - AZ won 28, drew 72 and lost none.

    A common theme in the games AZ won was the severe limiting of the mobility of one of Stockfish's bishops. It's like AZ figured out Stockfish's weakness, in that it overvalued immobile pieces.

    Another interesting thing that happened is a combination of moves that resulted in a repeated position. The second time the position arose, AZ opted for a different move, which begs the question, why didn't it play that move the last time?

    This isn't just huge for chess. This is huge for AI. Four hours it took for a completely different method of analysing chess to shit all over the previous best method of brute force. SF is processing nearly 100x more positions that AZ, but AZ has a superior understanding of the value of pieces based on their mobility.

    AZ is processing and learning, while SF is merely processing.

    Not sure if exciting or scary, but I have a boner.
    Last edited by OngBonga; 12-09-2017 at 02:02 PM.
    Quote Originally Posted by wufwugy View Post
    ongies gonna ong
  2. #2
    oskar's Avatar
    Join Date
    Apr 2008
    Posts
    6,914
    Location
    in ur accounts... confiscating ur funz
    All I see here is DeepMind developers screwing around on the job instead of working on SC2.
    The strengh of a hero is defined by the weakness of his villains.
  3. #3
    I see chess porn.
    Quote Originally Posted by wufwugy View Post
    ongies gonna ong
  4. #4
    Programming a computer to learn > programming a computer to do.

    They do the same thing with lots of AI applications, like machine vision. One the program knows what the end goal is, it basically teaches itself what to look for and what rules to apply. It's pretty cool.
  5. #5
    Why does a computer evaluate the same position differently?

    It's actually quite a profound question when you think about it. A basic understanding of what happened is required... AZ's rook was under attack from SF's knight, so AZ plays Rf6. SF moves the knight to attack the rook on f6, so AZ moves the rook back to f7. SF in turn moves his knight back so the rook is once again under attack, repeating the position from before. Now AZ plays Re7.

    So why didn't it play Re7 before?

    Best I can assume is quite scary... AZ is testing SF to evaluate its skill level. It's actively probing for weaknesses in SF's methods.

    Noone told it to do that, it taught itself to do that simply by being programmed to want to win at chess.
    Quote Originally Posted by wufwugy View Post
    ongies gonna ong
  6. #6
    Quote Originally Posted by OngBonga View Post

    Best I can assume is quite scary... AZ is testing SF to evaluate its skill level. It's actively probing for weaknesses in SF's methods.
    It isn't that at all it's because it's learning as it plays. It played a move that it evaluated as best then after having gained more information when the same position happened again it thought another move was better.
  7. #7
    spoonitnow's Avatar
    Join Date
    Sep 2005
    Posts
    14,219
    Location
    North Carolina
    Stockfish wasn't allowed to use opening books, which is an important part of the story you're missing in your OP.
  8. #8
    Trust spoon to come and shit on my dinner.

    I wasn't aware of that. I thought SF was loaded with human input, compared with just the rules for AZ. That said, SF was opening pretty solid. It was evaluating the games as very close to even right up until the endgame, at which point it has its "oh shit" moment and realises it's losing. At least, the ones I've been watching, which are all AZ wins.

    The openings are certainly not novel.
    Quote Originally Posted by wufwugy View Post
    ongies gonna ong
  9. #9
    Quote Originally Posted by Savy View Post
    It isn't that at all it's because it's learning as it plays. It played a move that it evaluated as best then after having gained more information when the same position happened again it thought another move was better.
    But the information it gained was a single move ahead, it can anticipate this move and already know it's not winning.
    Quote Originally Posted by wufwugy View Post
    ongies gonna ong
  10. #10
    It might have expected AZ to do something else the first time, or it may have just realised its first response was not optimal. Don't think it was trying to probe AZ for weaknesses. That's theory of mind shit and not something computers are capable of afaik.
  11. #11
    Quote Originally Posted by OngBonga View Post
    But the information it gained was a single move ahead, it can anticipate this move and already know it's not winning.
    The reason it's different is because it's constantly learning, it evaluated a move then it happened and could see further so when the move was repeated it then saw a better option. There is also the fact that it might realise that if it plays move A and the other player doesn't play the exact perfect move it's more winning and if it does it's repeated therefore playing move A first before trying the next best option of B is a better play.

    There are loads of reasons and literally none of it is trying to exploit how the player plays.

    Quote Originally Posted by spoonitnow View Post
    Stockfish wasn't allowed to use opening books, which is an important part of the story you're missing in your OP.
    How much difference do you think this would make? I've only really seen that a lot of people in the chess community are pretty blown away by it.

    It'd be interesting to see how quickly AZ caps out. You'd think the next step would be beating something like stockfish with an opening book.
  12. #12
    There is also the fact that it might realise that if it plays move A and the other player doesn't play the exact perfect move it's more winning and if it does it's repeated therefore playing move A first before trying the next best option of B is a better play.
    This is in line with my thinking that it's "probing for weaknesses". AZ plays Rf6, analysing it as the best move because SF's only sound response is repetition, which AZ can decline. So it "tests" SF to see if it can refute Rf6, and when AZ observes that indeed SF can refute that move, AZ chooses a different move which maintains its edge. This is a human thing to do... we're hoping for the quicker win thanks to the limits of our opponent. Why is AZ looking for the quicker win? Why does it value a quick win over a long win?

    I appreciate I'm just guessing as to its motive for playing a different move. It's just it raises interesting questions that I kinda like thinking about.
    Quote Originally Posted by wufwugy View Post
    ongies gonna ong
  13. #13
    spoonitnow's Avatar
    Join Date
    Sep 2005
    Posts
    14,219
    Location
    North Carolina
    Quote Originally Posted by Savy View Post
    How much difference do you think this would make? I've only really seen that a lot of people in the chess community are pretty blown away by it.
    No clue. It's just an important piece of the story that should be mentioned because traditional engines don't play the opening relatively well without them. The results are still pretty interesting and will definitely change the game for engine competition.
  14. #14
    oskar's Avatar
    Join Date
    Apr 2008
    Posts
    6,914
    Location
    in ur accounts... confiscating ur funz
    https://www.youtube.com/watch?v=4niz8TfY794

    This is the most concise explanation of what creativity is and how to cultivate it that I've ever heard. So much so that I don't have anything to add except: 12 tone music really is the perfect springboard for that topic. If it's irritating... that's kind of the point. It'll make sense later.
    The strengh of a hero is defined by the weakness of his villains.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •