neural-combinatorial-rl-pytorch
neural-combinatorial-rl-pytorch copied to clipboard
pemami4911
PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning https://arxiv.org/abs/1611.09940
Is this implementation useable for tasks where not all of the input is selected, but some subset of the input? I have seen partial implementation (such as the finish_symbol variable),...
Hi, for both the sorting task and the TSP task, when I run with any n_epochs > 1, toward the beginning of the 2nd epoch I get the following error...
The To Do mentions "Finish implementing beam search decoding to support > 1 beam". It looks like you have various beam width variables in different places of the code. Was...
a question
Hi, first thank you for your repo! I just want to ask you, is there a source from where I can understand more about the architecture of your work, besides...
mask
Hello @pemami4911, The problem really was with the mask. I've fixed it and the network started to learn. My Decoder now is: ``` class Decoder(nn.Module): def __init__(self, feactures_dim,hidden_size, n_layers=1): super(Decoder,...
can't find the SGD in criticnetwork and cant find the temperture in softmax
I ran main.sh (bash . /main.sh), I got this error. ~Validating~ 0%| | 0/1000 [00:00
It was a paper I was interested in and I am very grateful for your program. I have a question about the program. Sorry for the rudimentary question, I have...
Metadata
Owner
Metadata
PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning https://arxiv.org/abs/1611.09940