dh

Hi, @sungjae-cho and @Damcy I figured out the issue. Due to the particular way the algorithm was implemented (w.r.t dist_index & partition_number), I discovered there are a few constraints we...

Hm... okay, so it's probably about compilation of the extension... resize' is coming from the scikit-image library though -> it worked fine when using the original cts ... so I...

Hi, I am using python 3.5 and cython 0.25.2. Here you can check the code: https://github.com/RL-ninja/beating-montezuma/blob/master/algorithms/paac_cts.py FYI, I have not changed the cython code at all. The error happens when...

to clarify what I mean by [i=1, j=26], I do: ``` cpdef (double, double) _update(self, int[:, :] obs): ... for i in range(self.height): for j in range(self.width): ... print(i, j)...

Hi, I got it fixed. The problem was the state (game screen image) came as being of a uint8 type... and I just had to convert it to float64. Thanks...

@steveKapturowski I am running on HEAD of master branch w/ python2.7 tensorflow(cpu) 1.2.1 The command is: python2 main.py MontezumaRevenge-v0 --load_config config/dqn-cts.yaml -n 32

It's quite late but I have been using this hot fix. Not elegant but should do the job for those who remain on Octopress 2. Just need to modify your...