Zac Wellmer
Results
2
issues of
Zac Wellmer
I could be wrong but it does not seem that you are annealing the bias with important sampling as suggested in the PER paper(section 3.4). w_i = (1/N * 1/P(i))^beta...
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](https://github.com/hardmaru/WorldModelsExperiments/blob/244f79c2aaddd6ef994d155cd36b34b6d907dcfe/carracing/train.py#L304))? It seems...