News for hackers. Stuff that matters.

A comment on PID Without a PhD [pdf]. Parent comment

Re:PID Without a PhD [pdf] by 317070 on Monday February 26, 2024 @04:15AM (#39509157)
Generally yes and yes. But you will need _a lot_ more data and compute for reinforcement learning.

So RL is usually too cumbersome for relatively little gain.

Source: I'm a roboticist working with RL.

[ Parent | on HN ]
Re:PID Without a PhD [pdf] by moffkalast on Monday February 26, 2024 @07:36AM (#39510563)
Yeah I doubt there's much point without insane amounts of data, and if you do have the extra onboard compute a particle filter can probably leverage it more effectively.
[ Parent | on HN ]