This AI Learned Boxing…With Serious Knockout Power! 🥊
4,334,133
Published 2021-08-29
❤️ Watch these videos in early access on our Patreon page or join us here on YouTube:
- www.patreon.com/TwoMinutePapers
- youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join
📝 The paper "Control Strategies for Physically Simulated Characters Performing Two-player Competitive Sports" is available here:
research.fb.com/publications/control-strategies-fo…
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Aleksandr Mashrabov, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Mark Oates, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi.
If you wish to appear here or pick up other perks, click here: www.patreon.com/TwoMinutePapers
Thumbnail background design: Felícia Zsolnai-Fehér - felicia.hu/
00:00 Intro - You shall not pass!
00:49 Does nothing - still wins!
01:30 Boxing - but not so well
02:13 Learning is happening
02:39 After 250 million training steps
03:10 Drunkards no more!
03:29 Serious knockout power!
04:00 It works for fencing too
04:20 First Law of Papers
04:43 An important lesson
Károly Zsolnai-Fehér's links:
Instagram: www.instagram.com/twominutepapers/
Twitter: twitter.com/twominutepapers
Web: cg.tuwien.ac.at/~zsolnai/
All Comments (21)
-
"I fear not the AI that has trained in 10 billion simulations once. But I fear the AI that has trained in one simulation 10 billion times." - Bruce Lee probably
-
"Everyone has an algorithm 'till they get punched in the mouth." - AI Tyson
-
"After 130 million steps of training, it can not even hold it together" My life
-
The funny thing is that due to their bodies having the same measures, they've learned that cross countering was the best strategy. It would be interesting to see the same experiment, but with different measured characters.
-
0:50 I mean, I would also stop playing if my friend suddenly had a seizure.
-
An important thing to remember with these learning algorithms is that they're going from "less skilled than an infant" to "basic boxing" in *a week*. It sounds like a long time because we're used to computers operating in milliseconds, but imagine going from not realizing you have limbs to walking around and throwing punches in 7 days. That's a huge amount of learning, even in this simplified system.
-
I’d love to see a boxing simulation where one character has a shorter build or shorter wingspan and see how it adapts to its disadvantage
-
I think the reason the blue AI kept losing when the red AI fell over is due to over training for one possible outcome. The blue AI expected an attack and only knew how to win when it was being attacked but didn't know how to proceed when not attacked. It overcompensates for the expected attack and then falls over.
-
we should try to make a simulation where movement costs them energy to see if they would avoid too many small and fast movements
-
"this ai showcases agents that can learn boxing" red guy falls for no reason whatsoever "wait a minute -- that's the soccer ai, sorry"
-
Once the AI get so advanced you should save copies of individual behavioural patterns, name them, and start an arena. Maybe live stream fights? Would this not be awesome?
-
Having taught martial arts for a few years, it was surreal seeing how the ai was moving at different stages of their learning process. It looked remarkably like someone actually learning to fight.
-
Now I want to see an AI version of Robot Wars. Well described combatant rules, unlimited training. Last Bot standing wins.
-
AI has learned to never interrupt when its opponent is making a mistake.
-
This was strangely motivating we all start off stumbling but over time we learn and grow I’m glad these two stickmen can now box
-
Would love to see a future where AI in video games can dynamically adapt to what your doing, hopefully without them becoming impossible to defeat.
-
Should’ve taught Tyron Woodley some of this
-
As a fencer I'm really looking forward to what will it really evolve into. Just like when AI started becoming better in chess, we learnt a lot from them, and I believe same can be applied to more physical sports. What a time to be alive!
-
The rear hand/power hand should offer an increased reward (just like a real cross offers increased power and damage if it lands) over the jab hand to stop it from becoming a stiff jab stalemate every exchange, and having fighters with slightly different dimensions as many others have said would also be a good change
-
This is the second video I have seen from Two Minute Papers. Excellent cutting edge content. Well done.
