Conversation
Adds MicroDuckPolicy under torchrl.modules.tensordict_module, exposing TaskConditionedEncoder, GaussianHead, and a factory for the published walker. MicroDuckPolicy.from_pretrained() downloads the pinned walker.ckpt from torchrl/microduck-skills and returns (frozen_actor, ordered_task_library, action_scale). from_checkpoint accepts a local path for the same rebuild. The factory mirrors examples.microduck.ppo_mujoco.make_models so loading the published weights produces bit-identical parameters and outputs; TaskConditionedEncoder and GaussianHead become canonical torchrl modules (the gait residual head stays example-side since the published walker did not use it). Co-Authored-By: Claude <noreply@anthropic.com>
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/4394
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 057cdb2 with merge base 2d258fe ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
github-actions
Bot
added
Documentation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds MicroDuckPolicy as a focused public factory for the published recurrent MicroDuck walker.
API quality
Implementation-only network helpers are private. Public factory methods carry explicit return types. Imports remain at module scope except for the optional Hugging Face dependency and a documented lazy MicroDuckEnv import needed to avoid an env/modules cycle.
Tests