This algorithm beats CMA-ES (kind of like the LSTM of the ES world) for a few tasks. CMA-ES (from Nicolaus Hansen) is still my algorithm of choice for blackbox optimisation. I wonder if this algo will consistently beat CMA-ES on a variety of different tasks and make me use it ..
-
-
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Four months later...I notice that although Fig 1a, tweeted above, shows a typical ES "cloud" of many white dots centered at the current "genotype", in the methods it sounds like there are actually just two points in the cloud, i.e. a single "sample pair", P=1. Is this correct?
-
Using such a tiny "population" size for so many generations strikes me as rather strange. It would be a major revision, but it might be worth it to scale P to a more standard setting. To be clear, I think this is very nice work and I look forward to reading more from your group.
- Još 1 odgovor
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
香港人
⠀