[Question] Output shape of heads

jannerm / trajectory-transformer

Code for the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem"

https://trajectory-transformer.github.io

MIT License

464 stars 65 forks source link

[Question] Output shape of heads #8

Closed jsw7460 closed 2 years ago

jsw7460 commented 2 years ago

Thank you for such an interesting work.

Im really interested in your works and trying to understand your code, but I wonder about why the head network outputs the "#vocabulary + 1". Can you explain this for me?