pytorch / pytorch/rl

[RFC] Introducing transform primatives for sim2real

Open
#4,422 4 comments 0 reactions 1 assignee View on GitHub

@vmoens is already working on this.

Since Sep 17, 2026.

enhancement
Dominant language
Python
Stars
3.6k
Forks
487
Avg merge
1d 1h
Merged PRs (30d)
207

Description

##Summary:

  • Six transforms for sim-to-real + Compose recipes over existing mechanics.
  • DomainRandomization needs a small protocol on EnvBase.
  • these are the primatives i think we need to introduce:
    ObservationDelay, ActionDelay,
    ObservationNoise, ActuatorModel, SymmetryAugmentation, DomainRandomization.
    DomainRandomization
    ##RFC decision for domainrandomization interaction with sim
    • A. EnvBase.physics_param_spec + set_physics_params(td); transform samples in _reset.
    • B. Config field on MujocoEnvBase. Not composable, not loggable, no Isaac Lab path.
    • C. Transform mutates env.unwrapped directly. No spec, breaks under ParallelEnv.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.