Hear the story of how we used Python and machine learning to build an artificial intelligence that plays Super StreetFighter II on the Super NES. We’ll cover how Python provided the key glue between the SNES emulator and AI, and how the AI was built with gym, keras-rl and tensorflow. We’ll show examples of game play and training, and talk about which bot beat which bot in the bot-v-bot tournament we ran.

Talk given by Adam Fletcher and Jonathan Mortensen at PyCon 2018.

Thanks to PyCon for giving us permission to post this talk. freeCodeCamp is not associated with this talk. We’re just excited to bring more exposure to to it!

Learn to code for free and get a developer job:

Read hundreds of articles on programming:

And subscribe for new videos on technology every day:

Nguồn: https://chapelhilltownguide.com/

Xem thêm bài viết khác: https://chapelhilltownguide.com/game/

21 Comments

  • MavVRX
    Posted July 27, 2020 4:44 am

    What does the agent do the player swaps sides? Was it trained on both sides or was the input and controls flipped to handle that?

  • Neux
    Posted July 27, 2020 4:44 am

    gottem

  • Daniel Dilly
    Posted July 27, 2020 4:44 am

    12:49

  • Steven Barnes
    Posted July 27, 2020 4:44 am

    A 30-minute presentation without actually seeing the results of their efforts. I wish Google's AI was clever enough to not show me these videos.

  • Walter Hoekstra
    Posted July 27, 2020 4:44 am

    7:02 someone missed a typo in code review. damange done 😉

  • TCG Investments
    Posted July 27, 2020 4:44 am

    If you came here to see this actually work….. turn back.

  • Blah Bleh
    Posted July 27, 2020 4:44 am

    Please cc I wanna do this !! llearn soething !!..?
    YYYAAAYY IM GON222 TRIII IDSSS
    THIS * THANK YOU !!!

  • Blah Bleh
    Posted July 27, 2020 4:44 am

    i SOOOO wanna do this man !! 🙂 thanks !!!

  • ZHICHENG LIU
    Posted July 27, 2020 4:44 am

    I can take off my eyebrow
    ( ・ิω・)ノิิ
    ( ・ิω・ิ)put on
    ( ・ิω・)ノิิtake off
    ( ・ิω・ิ)put on
    ╰ิิ( ・ω・)ノิิtake off both sides
    ( ・ิω・ิ)put on
    ╰ิิ( ・ω・)ノิิtake off again
    (・ω・) No! I lost them!

  • Cat M
    Posted July 27, 2020 4:44 am

    Ultimate Machine Learning Super Street Fighter II Turbo HD Director's Cut Game of the Year Edition

  • ت
    Posted July 27, 2020 4:44 am

    [spoiler] you won't see a fight…

  • Jason Something
    Posted July 27, 2020 4:44 am

    Fascinating. Fighting games and artificial intelligence are both interests of mine and I'd love to see more development of AI in these games.

  • Zes
    Posted July 27, 2020 4:44 am

    no such thing as borx or nerdx or not, use ai as tool is ok, not nerx, cepux, any be any interesx, no nerx

  • 70ME3E
    Posted July 27, 2020 4:44 am

    whoa what, the presentation just ended when I thought it was just getting warmed up..
    where was the main model's architecture shown? you talked about some boring infrastructure setup stuff and about your cute on site display but not the main part??

  • Jimmy Joe
    Posted July 27, 2020 4:44 am

    Do it for fortnite

  • Matheus Prandini
    Posted July 27, 2020 4:44 am

    Would it be possible to do the same approach to other snes games?

  • nakobots
    Posted July 27, 2020 4:44 am

    Would have liked to hear more about the observation space. From the talk we heard x position and health bars are observed. I wonder what else about the opponent's action is known to the agent.

  • #Яков
    Posted July 27, 2020 4:44 am

    wow! so +++++ interesting
    great questions from audiences

  • Luke Wells
    Posted July 27, 2020 4:44 am

    Came here to see a match. 🙁

  • Daporan
    Posted July 27, 2020 4:44 am

    Awesome use of machine learning! If you like AI applied to games you might want to give my channel a check. Cheers!

  • Shadow Gallery
    Posted July 27, 2020 4:44 am

    A revolution without dancing is a revolution not worth having.

Leave a comment