Skip to content

Refactor policy network code and remove LSTM as default#393

Draft
riccardosavorgnan wants to merge 1 commit into3.0from
ricky/refactor_policy_remote_lstm
Draft

Refactor policy network code and remove LSTM as default#393
riccardosavorgnan wants to merge 1 commit into3.0from
ricky/refactor_policy_remote_lstm

Conversation

@riccardosavorgnan
Copy link
Copy Markdown
Collaborator

@riccardosavorgnan riccardosavorgnan commented Apr 9, 2026

Still WIP: refactoring of the neural net code for the policy plus remove the LSTM as default (MLP policy is now default)

return logits, value


class MultiDiscreteDriveLSTM(Policy):
Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is still WIP, it might contain incomplete method and serious bugs.

Comment thread tests/test_puffernet.py
assert_near(output_puffer, output_torch.numpy())


def test_drive(batch_size=1, input_size=512, hidden_size=512):
Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

will re-introduce before final review

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

rejected

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants