APS 95.43 is crazy

Jump to navigation Jump to search

Getting at least 70% against everyone . . . And more than 80% survival, did you get an extra batterypack or so ?

GrubbmGait (talk)13:12, 10 January 2024

I think it's more like adding five 0.1-APS improvements rather than one big change. I added some details to BeepBoop/Version History and BeepBoop/Understanding BeepBoop‎‎!

--Kev (talk)17:36, 10 January 2024

That is very solid. Btw how can you sure that each changes grant you positive APS since it’s very small, being hard to evaluate.

Xor (talk)02:45, 11 January 2024

I do test changes against a big subset of the roborumble bots (with many seasons to make sure results are significant)

--Kev (talk)17:42, 11 January 2024

Thanks, that sounds practical. I’m always doing a few seasons on the full population to test out small changes, which takes a few hours on newest hardware. However, it is still hard to make 0.1 APS changes significant.

Xor (talk)02:57, 17 January 2024

Yeah, you need to run a lot of seasons, but of course that's slow. I think the right way to develop a strong bot would be to operate like the stockfish chess engine where every change is evaluated for improving performance, but I mostly just develop on my laptop so I don't have enough compute to do that.

--Kev (talk)03:35, 19 January 2024