Max Lapan

@sbromberger any news about merging this functionality into LightGraphs? It still could be very useful for small graphs. For example, recently I started to rewrite Dagitty R package for causal...

@AI-Guru JFYI, I've implemented more or less accurate Gym version of deeptraffic environment. Going to opensource it after the competition. Probably it could be merged into gym as well.

@jackft I have couple of questions about implementation, it would be nice to have answers without js-code reverse engineering :) First one: how input to the network is formed? I...

@AI-Guru Yep, sorry for delay :) There is my repo with gym-compatible DeepTraffic environment: https://github.com/Shmuma/deep-traffic-2019 It includes environment with tests, training and playing code and not fully finished pytorch ->...

In principle, as a first step the following extensions could be implemented: * for producer nodes, approximate output rate should be definable as parameter * for consumer nodes, consumption rate...

Hi! If you still need it (after 3 years), there is my port to 3.7 I'm using in my projects: https://github.com/martinling/imusim/pull/11

Faced the same issue during my port creationg (https://github.com/martinling/imusim/pull/11). Solved by turning CYTHON_INLINE into empty declaration in the beginning of the file.

> We need some time to figure out what to do with this PR. I'll come back wth more information after this release cycle end. Sure, no rush! If you...

Thanks for the reply! What do you think about using backward hook for the noisy parameters resampling? From my naive perspective looks like a proper way to execute code only...

> Also am I right to think hat the noise should not be synced with the policy used for inference? Good question, need to reread the paper. From my understanding,...