Training AI Bots to Fight (they started dancing)

157,474
0
Published 2024-05-30
Twitter: twitter.com/cozmouzz
Discord: discord.gg/S2ZeaPMjdx
Patreon: www.patreon.com/cozmouz
Mail: [email protected]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Video showcases AI trained using Deep Reinforcement Learning and Imitation Learning.
Music By Epidemic Sounds.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

artificial intelligence, ai, machine learning, ai learns, deep reinforcement learning, ai training, evolution, neural networks, cozmouz #ai
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Chapters:
00:00 - Intro
00:52 - Neural Networks
01:39 - Observations
02:40 - Actions
02:55 - Rewards
03:52 - 1st Training Session [ Failed ]
04:50 - 1st Training Session Analysis
05:38 - Transfer Learning & Imitation Learning
07:18 - Balance Training Session
08:50 - Balance Training Session Analysis
09:30 - Further Changes
10:04 - Fighting Training Session
10:39 - Final AI Agent Fight [ Best of 10 ]

All Comments (21)
  • @cozmouz
    For those curious, Tensor-Board graphs for the final trained model showed "block frequency" way higher than "punch frequency". For some reason the AI resorts to blocking more than punching. I will be sharing more data and answering questions regarding the simulation over on Twitter: x.com/cozmouzz
  • @gat0anonimo
    Mfs had hundreds of millions of fights just to end up fighting like my drunk uncle
  • I would say that you need to keep an energy parameter. The reason we don’t see fighters constantly using these dance movements is because it would drain their energy. Add a limited energy parameter and you see better results.
  • @lastyhopper2792
    That's what happened when there's no energy cost for every movement. The fighters' movements simply become erratic.
  • @fractgate6824
    Yellow: shallow and consistent strikes. White: either misses or leaves a crater in Yellow's ribcage
  • @midbell
    i am no longer afraid of AI killing off the human race
  • @cris89631139
    It might look dumb at first glance but they are feinting each other faster than a human could almost instantly leaving no openings so they have to constantly change their angle of attack and cancel it/turn it into a feint midway through, maybe you could get better results if you train 1 AI to be proficient at attacking an evasive target that could also block (likely with motion capture), another one to be defensive by evading and blocking, and then combine both. Or maybe I'm just wrong and it will be the same result.
  • @micahkent4093
    I wonder what would happen if you were to add a reward of something like “making the least amount of movement, but causing the most impact to the opponent.”
  • We all been watching 15 min to see a snail brain to learn fighting 😂
  • @ln9593
    It can dance better than me at any rave
  • I think the reason it looks jittery is that they have the minimum possible reaction time. Meaning that they would react to the opponent's movement as soon as it happens. And if both avatars act like that, it would explain why the block frequency is higher than the punch frequency.. because both of them are reacting very quickly to any movements the opponent makes. Also if you have this in mind while watching the fight, you'll realise how cool these combat robots are, and that humans probably wouldn't be able to fight them in the ring
  • @RealKnarli
    This feels like watching 2 stand users fight but I don't have a stand