31–34 of 34 posts
NEAT: https://en.wikipedia.org/wiki/Neuroevolution_of_augmenting_t... NEAT > See also links to EANT. EANT: https://en.wikipedia.org/wiki/Evolutionary_acquisition_of_ne... : > Evolutionary acquisition of neural topologies (EANT/EANT2) is an evolutionary reinforcement learning method that evolves both the topology and weights of artificial neural networks. It is closely related to the works of Angeline et al. [1] and S…
Legendary Sethbling video from 2015 where he implemented NEAT for SMW: https://www.youtube.com/watch?v=qv6UVOQ0F44&t=1
Thanks for that link! There is another video posted 7 months ago from Seth where he interviews Ken Stanley, the creator of the NEAT algorithm. https://www.youtube.com/watch?v=5zg_5hg8Ydo
Earlier quoted context omitted.
> When I was in college in the early 2000s I played around with genetic algorithms and artificial life simulations on a cluster of IBM Cell Broadband Engine processors Early/Mid/Late 2000's I was working on a hobby project for artificial life with ga evolved brains. I spent a lot of time investigating options, like the cell processor (I bought a playstation to test with). I also looked at interesting multi-core cpu's…
> I ended up with a combo of CPU+GPU on networked PC's, which was better than nothing but not ideal. The biggest constraint I've seen with scaling up these simulations is maintaining coherence of population dynamics across all of the processing units. The less often population members are exchanged, the more likely you will wind up with a decoupled population and stuck in a ditch somewhere. Since modern CPUs can go s…
Agreed. For mine I purposefully avoided this problem by making the population+world relatively small (My dream was to scale this thing up significantly, but life intervened, maybe someday.
I post a link to NEAT here about once a week. The big problem is that NEAT can't leverage a GPU effectively at scale (arbitrary topologies vs bipartite graphs) Other than that, it feels like a "road not taken" of machine learning. It handles building complex agent behaviors really well, and pressure to minimal topology results in understandable and reverse interpretable networks. Its easier to learn and implement tha…
That being said, it's elegant and easy to reason about. And it's a nice intro into reinforcement learning. So definitely worth learning.