Page 3 of 3 FirstFirst 1 2 3
Results 21 to 24 of 24

Thread: AlphaGo Zero Article

  1. #21
    Basic Member
    Join Date
    Mar 2012
    Posts
    2,017
    I think it's more like a scenario across maybe multiple iterations/different outcomes or multiple scenarios, depending on what the learning task is.
    Explanations on the normal, high and very high brackets in replays: here, here & here
    Why maphacks won't work in D2: here

  2. #22
    Basic Member
    Join Date
    Mar 2012
    Posts
    2,017
    Quote Originally Posted by nostrademous View Post
    I swear that a long long time ago @ChrisC posted that there was a headless way to run Dota2, but don't ask me to find that thread.
    It's this one

    There's also this where I accidentally posted instead of here
    Explanations on the normal, high and very high brackets in replays: here, here & here
    Why maphacks won't work in D2: here

  3. #23
    Basic Member
    Join Date
    Dec 2016
    Posts
    76
    Quote Originally Posted by Siesta Guru View Post
    So what do you mean with simulator exactly? Are you trying to recreate the game?
    the minimal environment for me to test my algorithms.
    now there are tower melee creep and Hero for my NN to control.
    the simulator is very simple now,but enough for my usage.
    https://github.com/lenLRX/Dota2_DPPO_bots ----My ML bot work in progress

  4. #24
    Basic Member
    Join Date
    Dec 2016
    Posts
    731
    A youtube video briefly explaining the AlphaGo Zero approach:
    https://www.youtube.com/watch?v=vC66XFoN4DE

Posting Permissions

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