MAP-ELITES Bin Depth

[mathyouf]

We've selected a depth of just 1 for each niche (self.bins ) in our implementation of MAP-ELITES correct (only save the best result for that niche)?

Or is n_bins the depth, in which case we'd want to edit line 55 to insert the new performance if it is in the top n_bins fitness for that niche.

https://github.com/mathyouf/ELM/blob/main/map_elites/map_elites.py#L55

[herbiebradley]

Yes, I think we have depth 1, since the ELM paper refers to a single inhabitant for each niche. n_bins should be the size of each dimension (in the current code we can't have a non-hypercube behaviour space, but we should probably change that). To generalise our implementation we could add code to handle depth > 1, as you say, but that won't be immediately used for Sodaracers.

[herbiebradley]

Closed by #16, since we now have a history_length dimension in MAPElites.