How to train simple AIs to balance a double pendulum
143,115
Published 2024-06-05
XPBD article: matthias-research.github.io/pages/publications/XPB…
Github github.com/johnBuffer/Pendulum-NEAT
Music used (in order of appearance):
- Winterbeams by Diffie Bosman
- Empyrean by Dear Gravity (4000 pendulums part)
- Poison Message by Man with Roses
- The Endurance by C.K. Martin
All Comments (21)
-
Imagine training for 46 years and the god says, "naaaah, you wiggle too much"
-
I went from "Only a fool thinks he can balance a double pendulum" to "Praise the lord, he walked on water!"
-
My toxic trait is believing that I would be extremely good at balancing a double pendulum with zero practice.
-
the agent UI/visualization, the training graph hyper parameter view, the movitated loss function explanations.. all so well done wow
-
The idea of starting with lower gravity and higher friction is simply genius
-
The idea of gradually increasing gravity and reducing friction is just genius! Would be interesting to see if this method also would work for a triple pendulum 🤔
-
I didnt even think that it would be possible, wow, also nice editing and everything is just put in a way that makes the video really enjoyable 🎉
-
The next step is teaching an AI to balance a million pendulums. Keep up the great work, it's both educational and entertaining!
-
it was both surprising and entertaining to see the AI doing the blender move whenever the pendulum drops like a kid throwing tantrums
-
Your videos are always a delightful blend of programming, puzzles, science and philosophy. Thank you for making YT a better place <3
-
Very nice!, I really enjoyed the first video, it helped me create my own NN. Keep up the good work
-
👌🏼 Magnificent. It was really great idea to use air friction as the simplifying factor. I world love to see the cost of work in the evaluation function.
-
keep up making this content!
-
Love this approach of setting up an easier environment, for the ai to learn from and slowly increasing the difficulty. I would also love to see how you are going to explore this aspect in the future :D
-
9:03 "its a little better" AI: starts swinging the pendulum around like crazy
-
It's so interesting how friction and low gravity helped the AI learn. It's like humans practicing something complex in simpler variant, because trying to do something like balancing a double pendulum would completely overwhelm us too having no idea about how you would even start counteracting the imbalances
-
the progressive difficulty was an amazing training tool! very well put together video
-
It's amazing how you go above and beyond. After that first working solution, I would've been really proud of myself and be done with it, but you just make it better and better.
-
give this man a Nobel prize! respect!
-
The editing and the feedback UI are brilliant. Cheers, Pez.