Exploring Reinforcement Learning: Can AI Learn to Play QWOP? | Digi-Key Electronics

[@Dinkleberg96]

This is really interesting. I would love to learn more about A.I. I'm definitely staying tunned for the next episode! Amazing work as always Mr. Hymel!

[@willdelee3424]

@aaaq9ou

[@TheFxdstudios]

@@willdelee3424Ty Ty

[@BeckyStern]

Thank you Shawn!!! This is awesome. Unlike my QWOP skills. 😆

[@t.vigneshnayak7886]

we need ai related series, please bring more videos.

[@Moodie111]

A few things need to be added. First: the goal shouldn't just be covering the most distance, it should be covering the most distance in the least time. The video shows the runner essentially hopping on one foot. Imposing a fastest time goal would promote faster solutions using both legs. Second: code should be added to disallow sequential steps using the same foot, so that the only gait allowed would be left-right-left-right-left-right. These would be major improvements.

[@JSStrom]

That was very interesting indeed... Best

[@michaelnilan7413]

Great content 😍🤩

[@kalvincochran9505]

It’s not cheating it’s just a phenomenal idea. If you would have done that it probably would have worked better