# How does Hindsight Experience Replay cope with multiple goals?

What if there are multiple goals? For example, let's consider the bit-flipping environment as described in the paper HER with one small change: now, the goal is not some specific configuration, but let's say for the last $$m$$ bits (e.g. $$m=2$$), I do not really care if there is $$1$$ or $$0$$.

In the paper, there is section 3.2 multi-goal RL, where they mention an example with two-dimensional coordinates ($$x$$ and $$y$$), but they are interested only in the $$x$$ coordinate, so they only use the $$x$$ coordinate as a goal.

Applying this strategy to my example would result in cutting the last $$m$$ bits from the goal and only use the other bits. Is this logic correct?

Another approach I could think of would be to train with all possible goal configurations, as there are not many in my case. But this seems impractical as the number of goal configurations grows.