Finebouche
Finebouche
Hi, Could this [github.com/colesbury/nogil ](https://github.com/colesbury/nogil ) be related ? It is supposed to fix the current issue with the `n_jobs` feature.
Hey wanted to react to that, I don't think dandling nodes will add more bloat as the algorithm progresses as : * they are not use to compute the outputs...
Ok changed my mind. The problem with dandling nodes will be that genome modification can still only impact those dandling nodes and the algorithm can get stuck because most contribution...
From my experience anyway, it doesn't seem really useful. I always end up with so many disconnected parts. It really seems hard for the networks and weights evolution to make...
Ah alright, fixed that in this pull request as well : https://github.com/CodeReclaimers/neat-python/pull/282
Hi, actually I don't remove the dangling nodes from the genome, but only from the feed forward network use to do the inference. This way dandling node can still evolve...
Hi, Sure thing ! I made a nice little interface between Gym and neat-python so that you can use any gymnasium environment easily. Check this repo : https://github.com/Finebouche/neat-gymnasium It works...
Ah yes the lunar example is totally broken.
still same problem with 5.12 on: JabRef 5.12--2023-12-24--4233bad (sonoma) Mac OS X 14.2.1 x86_64 Java 21.0.1 JavaFX 21.0.1+6
> @Finebouche Could you try the build of today? https://builds.jabref.org/main/ No, still crashing