William Woof

Thanks Jaesik, As a general note, I don't think this implementation works completely in it's current state, at least in terms of creating a 'simulator'. I'm happy with the implementation...

Hi Jaesik, Using centripetal force eqn `a = v^2 / r` and gravitational eqn `F = ma = GMm / r^2` gives tangential velocity `v = sqrt(GM/r)`. I then set...

Par the course for DeepMind, unfortunately (although at least they are willing to provide comment). Did you ever get the loss numbers that they report in the paper? -Will

Do you want me to do a PR anyway, but with the abbreviations removed? It should be transparent above the schema level.

I was just about to make a separate issue for this, but I'll roll it into this one. I have been thinking about this issue a bit and this is...

I was't really commenting on your suggestion, just rolling the discussion into one thread. Also, [looks fine to me](https://i.imgur.com/015U3Ij.png)

Memory-wise I imagine the overhead of constructing dicts is negligible compared to the actual tensor operations, unless somehow a tensor itself is being copied. More importantly, the current way of...

If I understand the paper correctly, they don't differentiate through the DND (I can't say for sure either way though). The keys in the DND are not updated through the...

My understanding is that it's a bit like an adaptive kernel , but where stored values aren't updated. As for backpropogating though the table I don't really see how it...

Hi, Sorry for the late response. Revisiting this issue it seems that my implementation is incorrect, and that the stored keys should be updated in the dict via backprop. However,...