Is antithetic sampling doing anything for CMA-ES?

Open zacwellmer opened this issue 5 years ago • 0 comments

To me it looks like we are just re-using the same seed twice which would waste compute and effectively cut our population size in half(seen here in train.py)? It seems like we are only making use of antithetic sampling in OpenES and PEPG.

Am I missing something here?

Mar 08 '20 03:03 zacwellmer