Re: Robocode and reinforcement learning

Hi Matt,

thanks for sharing!

Do I see it well that it took 3000 rounds to learn to lock the gun on the
enemy ?
How much of that is done by you in feature selection ?
What's coming next ?

On Sat, Mar 13, 2021 at 6:06 PM Matthew Gerber <[email protected]>
wrote:

> I've been picking away at RL for robocode, and I thought this might be of
> general interest in this group. It's a work in progress here
> <https://matthewgerber.github.io/rlai/case_studies/robocode.html>. The RL
> framework is general-purpose and is described here
> <https://matthewgerber.github.io/rlai/>.
>
> Matt
>
> --
> You received this message because you are subscribed to the Google Groups
> "robocode" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to [email protected].
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/robocode/9523d0e6-7a3f-41ee-bc5c-5bde98cbfd97n%40googlegroups.com
> <https://groups.google.com/d/msgid/robocode/9523d0e6-7a3f-41ee-bc5c-5bde98cbfd97n%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
>

-- 
You received this message because you are subscribed to the Google Groups "robocode" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [email protected].
To view this discussion on the web visit https://groups.google.com/d/msgid/robocode/CABB%2B073o3i%3Dn3ESVZT65k%2Bna-gBDfQeGMfSpFFAOXjEOfyOhkQ%40mail.gmail.com.