neural-combinatorial-rl-pytorch icon indicating copy to clipboard operation
neural-combinatorial-rl-pytorch copied to clipboard

beam search

Open wasd12345 opened this issue 6 years ago • 0 comments

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 your note because:

  1. you implemented beam search but it didn't seem to work as well when width>1 and you wanted to investigate further, or
  2. there are still some places in the code that would need to be modified to before using beam search?

If 2), then which places would need to be modified?

Thanks!

wasd12345 avatar Dec 13 '18 07:12 wasd12345