Triple Pendulum on a Cart

> We don't know how to make AI that will learn to play even simple game like montezuma's revenge in some reasonable play time like 30 min. Explain to me why a Tool-assisted Speedrun doesn't count as "AI". Its certainly not a human who is playing that ( link ). > Something that could in one package: I'm not sure if that sort of thing is worth the investment. But if we have "Fly the F35 airframe" (which is incredibly unstable), then we suddenly reach "only computers can fly this thing" levels. Just the assumption of super-human control systems is baked into modern products. ▶ this video Our cell phones are largely manufactured by machines these days. A few tidbits here and there remain in human hands for cheapness... but a lot of today's stuff is basically an AI. link

Double and triple pendulums have been solved: ▶ this video I have little doubt cancer will be someday as well. It might not -- probably won't -- happen in my lifetime. But if humanity hasn't collapsed, I find it very unlikely that we're still dealing with cancer in a thousand years.

When you have mutliple vehicles, each potentially with their own variant of control software, then each could be internally deterministic but "foreign" to the other vehicle. Kind of like a double pendulum. Edit: But also like that cool double/triple pendulum thing ( ▶ this video ) you don't necessarily have to be able to predict the future if you are simply monitoring the present state at a high enough sampling rate. Note that this thing is sampling at 1ms. Not sure what kind of sampling would be necessary for cars, certainly a function of velocity and braking power.

Two-pole balancing (2009): link Double inverted pendulum balancing (2015), a much harder task: link Double inverted pendulum balancing with a physical cart (2011), a much much harder task: link Triple!!! inverted pendulum balancing with a physical cart (2011), a much much much harder task: ▶ this video

The single inverted pendulum balancing problem has been solved using neural nets, fuzzy logic, and nonlinear control theory. It's a standard problem in controls classes. Here's a system learning how to do this.[1] Takes about 200 trials. Here's the triple inverted pendulum balancing problem, solved using feedforward control.[2] [1] link [2] ▶ this video

Cool. Feature request: mount the pivot on a programmable cart. It'd be fun to write software to balance the double pendulum. e.g. link and, balancing a triple pendulum: ▶ this video