Update `_process_sequence()` docstring (#219)

Small modification in the documentation of `_process_sequence` to reflect the correct order (`hidden_state`, `cell_state`) of `lstm_states`.

See order here: https://pytorch.org/docs/stable/generated/torch.nn.LSTM.html
This commit is contained in:
Rogério Júnior 2023-12-05 04:59:48 -08:00 committed by Andreas Schaarschmidt
parent 94a5daab02
commit 1553b66ee4
1 changed files with 1 additions and 1 deletions

View File

@ -170,7 +170,7 @@ class RecurrentActorCriticPolicy(ActorCriticPolicy):
Do a forward pass in the LSTM network. Do a forward pass in the LSTM network.
:param features: Input tensor :param features: Input tensor
:param lstm_states: previous cell and hidden states of the LSTM :param lstm_states: previous hidden and cell states of the LSTM, respectively
:param episode_starts: Indicates when a new episode starts, :param episode_starts: Indicates when a new episode starts,
in that case, we need to reset LSTM states. in that case, we need to reset LSTM states.
:param lstm: LSTM object. :param lstm: LSTM object.