Jingwei Zhang

Installed but cannot import

3

Hey, * System configuration: `Ubuntu16.04`, `anaconda3`, `python3.6` * Output of `pip install vizdoom`: ``` Requirement already satisfied: vizdoom in~/anaconda3/envs/doom-env/lib/python3.6/site-packages (1.1.6) Requirement already satisfied: numpy in ~/anaconda3/envs/doom-env/lib/python3.6/site-packages (from vizdoom) (1.15.1) ```...

Hi, in line `137` of `feedforward_neural_doodle.py`, I don't quite understand why should the input masks be divided by 10 as in `inputs_batch:copy(masks_batch_/10)`? Thanks in advance! and thanks for the great...

possible error in `critic.py` `forward()`?

5

Very helpful repo! One question, in the `forward` function in `critic.py`, there might possibly be an error: In line `37`, the `Decoder` always takes in the same initial `dec_input` for...

Hi, Super cool and helpful repo! I'm having some trouble getting it run properly, could you provide the versions of `python` and `pytorch` and other packages to correctly run this...

issues with python version for python2.7

2

Hey, I've been using the lua version of this package and it's awesome, really great work! Now I'm trying out the python version, but am having this error: ``` >>>...

std / sqrt(len)

2

Hi, maybe I'm missing something obvious here, but could you inform me as why the `std` is divided again by `sqrt(len)` as this should already be taken care of in...

question regarding `_get_parallel_step_context`

1

Hi, thanks for making the code public! I have a question regarding the function `_get_parallel_step_context`: Here, https://github.com/wouterkool/attention-learn-to-route/blob/c66da2cfdc9ae500150bfc34d597a33631d2ceb3/nets/attention_model.py#L378, `num_steps` would always be `1` as the `current_node` reads the `prev_a` of the...

backward through cumprod

12

Hey, In function ```get_allocation_weight()``` in ```memory.py```, ```cumprod``` is used, but as far as I know, this operation does not have autograd support yet and is still in PR: [https://github.com/pytorch/pytorch/pull/1439](url), so...

Hi, When I try to do inference with the provided `model-119496`, I get the following errors, basically all `BatchNorm` layers are missing `moving_mean`&`variance` from the checkpoint: ``` util.py:106] Missing var...