Guillaume Lample

Hey, any update on this? We noticed that the more players in the game, the slower it is. When we make a match between 2 agents (+1 if we count...

Wouldn't it be more efficient to have each agent communicating its actions to the host only, and let the host inform every agent about the other agent actions? But still,...

Thank you. I prefer not to reinstall ViZDoom right now because I have some models currently running, but I'll try just after the deadline and keep you updated.

I wanted to transfer some information from the ACS script to python using this command. Right now it's a little bit difficult since I have to do it with the...

Thanks for your answer. `WhiteSpaceSplit` alone does not seem compatible with the `ByteLevelBPETokenizer`, is it? Typically, if I try to encode characters never seen before it will fail to decode...

We would also find this option very useful 👍 The workaround to have 1000 special tokens at the beginning is fine if there are just a few tokens, but is...

These are parameters of the model learned with back-propagation.

Token level I would say. You can check https://github.com/glample/tagger/blob/master/evaluation/conlleval

What does the full log file contain? Could you check this is not a problem with permissions and that the script is allowed to create this scores file in the...

1) Jointly learning the code is mostly useful when you share the embeddings. It's good because it helps the model handling rare words like named entities very easily. Even if...