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:
parent
94a5daab02
commit
1553b66ee4
|
|
@ -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.
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue