# Do bi-directional RNNs necessarily use 100% teacher forcing?

I typically think of teacher forcing as optional when training an RNN. We may either:

• use the output of time-step $$t$$ as the input to time-step $$t+1$$

• use the $$(t+1)$$th input as the input to time-step $$t+1$$

When I actually sat down to write a bidirectional RNN from scratch today I realised it would be impossible to do without 100% teacher forcing, because each time step needs access to the "history" going back to the 0th time-step (forward direction) and going back (or forward - however you want to think of it) to the last time-step (backward direction).

Is that correct?