Hi, I was wondering why the hidden_states are not being reset when the episode ends in the learn_vision pipeline from the on_policy_runner. I know that they are being detached but when the robot gets reset shouldn't it also have a fresh hidden state of none instead of the previous episode's hidden_state value ?
You are right. But we found this does not affect training but saves a lot of effort if you want to find all terminating envs and reset corresponding hidden states.
Hi, I was wondering why the hidden_states are not being reset when the episode ends in the
learn_vision
pipeline from theon_policy_runner
. I know that they are being detached but when the robot gets reset shouldn't it also have a fresh hidden state ofnone
instead of the previous episode'shidden_state
value ?Thanks for the amazing repo..