Environment step count with frame-skip about curl HOT 3 CLOSED

reported results are low-level DMC environment steps (1k per episode)

from curl.

Quick follow-up after reading "Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels" by Kostrikov et al., in which they state:

In contrast to prior work, CURL [42] plots returns as a function of modified environment steps, i.e. true environment steps divided by the action-repeat hyper-parameter.

Is their assertion then wrong? Thanks!

from curl.

we count environment steps (100k env steps = 25k agent steps with action repeat of 4), please refer to section 5.1 https://arxiv.org/pdf/2004.04136.pdf

from curl.