Neil Traft

I've recently realized that this has long been a topic of debate in evolution more broadly: is "neutrality" beneficial or harmful? Is it an important feature of evolvability? (I.e., modifications...

I also just tried to download TransNAS-Bench and found the link was broken. However, it is still available [via Google Drive](https://drive.google.com/drive/folders/1HlLr2ihZX_ZuV3lJX_4i7q4w-ZBdhJ6o). See [this issue](https://github.com/huawei-noah/vega/issues/290).

@MarieLanger Is this actually the reason for the fluctuations you're seeing? If a species is marked as stagnant, then it should not appear in the next generation at all, should...

@MarieLanger `is_stagnant` is only true if the species is being removed in this generation. See [this line](https://github.com/CodeReclaimers/neat-python/blob/37bc8bb73fd6153a115001c2646f9f02bac3ad81/neat/stagnation.py#L70). "Stagnant" means `max_stagnation` has been _exceeded_. Otherwise all species would always "stagnant" except...

Right so it seems we have a deeper issue here. I guess the next thing to look at is to track the actual elite individuals, and figure out what is...

Okay, I believe I've figured it out. First, by looking at `mmcls/tools/train.py`, I can see that your `train.py` is an older/simplified version of that. I see that `--gpus` has been...

As I look into this further, it really does seem like it's not intended for any node in the graph not to have inputs. Many of the aggregation functions throw...

I have read the [original NEAT code](https://nn.cs.utexas.edu/soft-view.php?SoftID=4) (C++, from Stanley's thesis, 2001), and indeed have found this note before disabling a connection: > ``` > //We need to make sure...

Oh, really?? As in, you were able to "solve" the Lunar Lander, or at least do well? I assumed that it never worked, when I started using this package ~9...

Note some other issues that are suspicious and may be part of the problem: - #272 - #271 I think elitism isn't working correctly, and best genomes might not be...