Add vanilla RNN support to RecurrentPPO
#296
Open
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR extends the
RecurrentPPO
implementation to support vanilla RNN layers (nn.RNN
) in addition to the existing LSTM support. Users can now choose between LSTM and vanilla RNN through therecurrent_layer_type
parameter inpolicy_kwargs
.Context
RecurrentPPO
#295)lstm_*
variable names (e.g.,lstm_hidden_size
,n_lstm_layers
) to avoid breaking existing code. I'm open to renaming them to more neutral names (e.g.,hidden_size
,n_layers
) if the maintainers prefer, but wanted to prioritize backward compatibility in this initial implementation.Types of changes
Checklist:
make format
(required)make check-codestyle
andmake lint
(required)make pytest
andmake type
both pass. (required)