AI Learns SUPER SMASH BROS

Поділитися
Вставка
  • Опубліковано 27 лис 2024

КОМЕНТАРІ • 80

  • @pareak
    @pareak 5 днів тому +18

    Honestly, the most impressive part of this video is the reward-graph at 1:39. There still seems to be even more space left to become better at the game for the AI. It's also quite amazing how simple your rewards were. You could have make it so much more complex. Anyway, great video, love your stuff, keep it up!

    • @aitango
      @aitango  5 днів тому +4

      Yeah it always amazes me that the AI just seems to keep improving no matter how long I leave it for. Also makes me wish I had more compute!

  • @aname4390
    @aname4390 5 днів тому +12

    I know brawl isn't the most popular one, but holy smokes it would be wild to see this go up against an expert.

    • @viewerguy10
      @viewerguy10 4 дні тому +1

      I think it would need more training at first to keep up since humans play differently. But it would probably dominate after a while

  • @kevinjuarez9252
    @kevinjuarez9252 5 днів тому +11

    I want you to team up with Code Bullet and Challenge Red Falcon to another Mario Kart AI vs Human duel!

  • @nobafan7515
    @nobafan7515 5 днів тому +14

    I am a simple viewer.
    Ai tango uploads a vid,
    I watch.

    • @aitango
      @aitango  5 днів тому +4

      True loyal subscriber! Especially since I recognize your name haha

  • @arikgorun6004
    @arikgorun6004 5 днів тому +13

    Congrats on the paper! Knew as soon as you said bleeding edge it was your own model you talked about in you past livestream😆.
    I just read the paper and it's really detailed, and a great advancement for the accessability of RL research as a whole!
    I was not aware of Manchausen and it's pretty awesome.
    Also this is by far the lowest replay ratio I can remember being used in SOTA RL, so that's really impressive.
    Your analysis of action gaps and Dormant Neurons is really insightfull and I wish more papers in the field offered similar stuff.
    Again congratulations and good luck with the submission!
    P.S. Any chance of getting more detailed results on Procgen👀? jk jk. Unless?

    • @aitango
      @aitango  5 днів тому +6

      Really grateful for the mini-review on the paper! What more results do you want? The individual game scores are in the appendix, or were you hoping for something else? Sadly the reviewers at the conference I submitted to weren't as impressed :'(

    • @nikolozgilles
      @nikolozgilles День тому +1

      @@aitangowhaaat you wrote that paper? cool

  • @fluffsquirrel
    @fluffsquirrel 5 днів тому +4

    12.5 days of training is crazy! Thank you for choosing the perfect game to showcase the new "Beyond The Rainbow" algorithm!

  • @nickikonomidis5027
    @nickikonomidis5027 5 днів тому +5

    It would be really dope to see it fight level 9 CPUs or do Cruel mode. Also, could you do this for Melee too, or only for Wii games?

  • @Leeeiif
    @Leeeiif 5 днів тому +7

    lets watch it again

  • @SupremeRTS
    @SupremeRTS 5 днів тому +29

    Real OG's know this is a re-upload

    • @aitango
      @aitango  5 днів тому +10

      Old video got a copyright claim unfortunately

    • @rembartx
      @rembartx 2 дні тому

      @@aitango do liars bar

  • @Benthesuperai
    @Benthesuperai 5 днів тому +4

    yo ai tango i've been making ai's for video games just like you bro you were my inspiration to learn how to code these things :)

    • @aitango
      @aitango  5 днів тому +4

      That's really cool to hear, always love to hear people wanting to learn about RL and similar things

  • @TheBena007
    @TheBena007 3 дні тому

    Never seen a good smash bros AI before, this one is the best so far. Now we only need it to 1v1 itself on random characters to create the ultimate smash bros pro

  • @Kinglux8
    @Kinglux8 5 днів тому +3

    Been waiting for a new video 🎉

    • @aitango
      @aitango  5 днів тому +2

      Hope you enjoyed it!

  • @staleeyez
    @staleeyez 2 дні тому

    I'd love to see what a new AI would do vs a lvl 1 amiibo in Smash 3DS. Having them both race for development might be fun to watch.

  • @Ninjakurl7
    @Ninjakurl7 5 днів тому +2

    that mario AI spams UP B as much as a pikachu main that is annoying

    • @aitango
      @aitango  5 днів тому +1

      I can’t really blame it, it seems to be quite effective

    • @Ninjakurl7
      @Ninjakurl7 4 дні тому

      @@aitango no one i know like playing with that Pikachu main becasue we kinda play competitivy

  • @JoshuaKing-nc9rj
    @JoshuaKing-nc9rj 5 днів тому

    It is incredible to see how far your videos have come, your ai's are really impressive and only seem to get better!

    • @aitango
      @aitango  5 днів тому

      Thank you! From the AI side things are so much better now, I can’t believe how bad they were when I started!

  • @stevo13131313
    @stevo13131313 5 днів тому +2

    What’s a normal score to be able to compare how the ai did

  • @IrishAnonymous01
    @IrishAnonymous01 5 днів тому

    I'd be interested in a behind the scenes video detailing every step of the process in setting this up. A tutorial almost.

  • @viewerguy10
    @viewerguy10 4 дні тому

    Dude this is like a real time tool assisted speedrun. Very cool.
    Edit:
    If I’m not mistaken the ai is using a technique called momentum canceling as well. It’s air dodging after getting hit to last longer. That’s impressive.

    • @aitango
      @aitango  3 дні тому

      Oh that’s pretty cool, I had no idea why the AI was doing that!

  • @ephanitor6741
    @ephanitor6741 3 дні тому

    I am really not into Smash Bros, but I knew your vid woud catch me anyways ;) Also your editing skills seem to have evolved again. Great job, keep it going :)

    • @aitango
      @aitango  3 дні тому

      Thanks, really great to hear!

  • @HenryKopelson
    @HenryKopelson 5 днів тому

    This is really impressive. Love the content you create!

    • @aitango
      @aitango  5 днів тому

      Really nice to hear, thank you!

  • @moomanchicken6466
    @moomanchicken6466 5 днів тому

    If you implemented this AI architecture yourself from the paper published only 2 weeks ago that's really impressive

    • @aitango
      @aitango  5 днів тому +1

      I wrote the paper lol

  • @BeastlyGamer191
    @BeastlyGamer191 5 днів тому +1

    How can I see the paper? Beyond the Rainbow and that snippet sounds really interesting

    • @aitango
      @aitango  5 днів тому +1

      Link to the paper is in the description!

  • @cantuncpekkan4001
    @cantuncpekkan4001 3 дні тому

    How do you find papers on algorithms? I really want to start reading papers.

  • @the1whoplayz
    @the1whoplayz 4 дні тому

    ngl the thumbnail is super misleading (I thought this was gonna be for ultimate given the Ultimate Mario render and Ultimate Battlefield)
    aside from that, this video was still super interesting

  • @basketjason
    @basketjason 4 дні тому

    This is amazing. I'm humbled by the fact that I don't understand why this isn't causing an uproar in the research community. Maybe because it's not a pure approach, but rather a Frankenstein of different techniques? So what? I don't get it.
    I skimmed the paper, and will be studying it later. I love the simplicity and feel I'll learn from it. I'm thirsty for the supplementary materials - especially the code! Where can I find it?

    • @aitango
      @aitango  3 дні тому

      The supplementary material is available on the open review submission to ICLR, however I soon plan on doing a more polished repo for it. My reviewers don’t seem as impressed haha

    • @basketjason
      @basketjason День тому

      @@aitango Cool! I'll be keeping an eye on your progress

  • @reubenoakley5887
    @reubenoakley5887 3 дні тому

    Do you think there's a way you could encourage it to use items? It never grabbed a single one as far as I could tell

    • @aitango
      @aitango  3 дні тому +1

      I could give it a reward for doing so. I was quite surprised it didn’t to be honest

  • @MrCreeperphile
    @MrCreeperphile 5 днів тому

    I may have miss the information but what do you use ass first layer ?
    In other words how do you give at the ia it position, enemies position, percentage and all other information on screen?

    • @aitango
      @aitango  5 днів тому +2

      The AI is just given the raw screen pixels as input. I don't explicitly given it the position or enemy position

  • @nobafan7515
    @nobafan7515 5 днів тому

    I'm curious, was it playing 4 instances of brawl each at 2x speed?
    Also, do you just launch the emulator 4 times to get the extra ai training, or do you have to have 4 different verdions of the program?

    • @aitango
      @aitango  5 днів тому +1

      Its just 4 emulators so the AI can practice 4x faster. In theory I could make the agent try different things in each emulator (such as exploring more in one than another).

  • @tiinpa7093
    @tiinpa7093 5 днів тому

    I don't see the supplemental materials the paper references. Is that still forthcoming?

    • @aitango
      @aitango  5 днів тому

      They were submitted to the conference the paper was submitted to, I’m not sure if it’s publicly available yet. If it get accepted it will be for sure

  • @mehvix
    @mehvix 3 дні тому

    how does it generalize, i.e. harder CPUs / varying opponent characters / vs human

    • @aitango
      @aitango  3 дні тому

      Probably not well with no extra training. If I let it train on harder opponents it would probably be pretty good though

  • @trulyinfamous
    @trulyinfamous 5 днів тому

    Your voice is far too quiet in this video. It's kinda hard to hear you with the music being of similar volume as well. That said, these vids are always cool.

  • @fluffsquirrel
    @fluffsquirrel 5 днів тому

    Hey what about trying this algorithm on Syoban Action? (Cat Mario)

  • @PaulEffinger
    @PaulEffinger 5 днів тому

    I know you got copyrighted, but what exactly caused that? I’m curious, but if you don’t know either, no biggie.

    • @aitango
      @aitango  5 днів тому

      One of the songs! We thought it was non-copyright, but we were sadly wrong

  • @9Sleepyhead5
    @9Sleepyhead5 11 годин тому

    How dose the ai see? Because it looks like a blind person playing just getting told how many opponents are ko and how long it was going on for

    • @aitango
      @aitango  8 годин тому

      The AI is given an image of the screen, and uses a convolutional neural network to learn how to interpret images. This isn't just a sequence of actions, I could start this AI in any position and it could still play

  • @FormulaHavocOrland
    @FormulaHavocOrland День тому

    Jeez wow

  • @SsbMewtwo
    @SsbMewtwo 5 днів тому

    Why brawl and not Melee, or P+?

    • @aitango
      @aitango  5 днів тому

      I played it as a kid so am inherently biased haha

  • @sas7782
    @sas7782 5 днів тому

    🐐🐐🐐🐐🐐🐐🐐🐐🐐🐐

  • @anonym5160
    @anonym5160 5 днів тому +2

    Why reupload?

    • @aitango
      @aitango  5 днів тому +5

      Old video got a copyright claim sadly

  • @Random_Guy-rm4tv
    @Random_Guy-rm4tv 5 днів тому

    re-upload?

    • @aitango
      @aitango  5 днів тому +1

      Old video got a copyright claim :(

  • @rizzmox4118
    @rizzmox4118 5 днів тому +2

    reuploaded for double view #scam

    • @aitango
      @aitango  5 днів тому +5

      Old video got a copyright claim :(

    • @rizzmox4118
      @rizzmox4118 5 днів тому +2

      @@aitango just kidding great video good sir!

  • @JohnLattanzio98
    @JohnLattanzio98 5 днів тому

    Whats with the reupload?

    • @aitango
      @aitango  5 днів тому +1

      Old video got a copyright claim :'(

  • @rizzmox4118
    @rizzmox4118 5 днів тому

    invest in NNE!!!!!

  • @cantuncpekkan4001
    @cantuncpekkan4001 3 дні тому

    How do you find papers on algorithms? I really want to start reading papers.

    • @aitango
      @aitango  3 дні тому

      Find a good and very popular paper, then just use the papers it cites to find more relevant stuff. My paper is in the description if you want to read that