Fair point, but it's worth noting that there is a trade-off between # seeds, # baselines, and # and complexity of environment(s). Personally, I'd prefer a method /w 3 seeds eval'd on 57 tasks with 5 baselines to one with 10 seeds eval'd on 1 task with 2 baselines.https://twitter.com/pyoudeyer/status/1222911050028285954 …
-
-
Odgovor korisniku/ci @Zergylord
Tasks are not a straightforward replacement for seeds because seends can be randomised, and hand-made tasks are not. Unless you're procedurally generating the tasks, in which case you effectively have more seeds.
0 proslijeđenih tweetova 0 korisnika označava da im se sviđa
Odgovor korisniku/ci @RWerpachowski
I agree, not a replacement -- but they do compete for computing resources. And generally I've found that it's easier to overfit to a single task than it is to be misled by too few seeds. Both are problematic, but without infinite compute hard decisions must be made.
15:50 - 30. sij 2020.
0 replies
0 proslijeđenih tweetova
1 korisnik označava da mu se sviđa
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.