lker

Also tried replacing `FastLSTM` with `GRU` with everything else being the same, that did not converge after running it longer interestingly.

@JoostvDoorn haven't got around to it since, but probably takes a few lines to add to rlenvs.

@Kaixhin yes this is needed for async, just created #47 to do it a bit differently.

My first step is to implement a CTS based probability measure for small bitmaps (with 1 bit pixels) with the location dependent model described in the paper. I will expect...

The paper refers to a number of other papers with regards to CTS usage saying "similar to this and that", but in the end the referred papers do quite different...

Kind of finished a separate [module](https://github.com/lake4790k/pseudo-count-atari) with the native probability tree for 8 bit screens. Was not easy, but probably now comes the difficult part... for example the probablity of...