Upload README.md with huggingface_hub

30df6c9 verified 24 days ago

1.15 kB

license: other
library_name: jax
tags:
  - warp-rm
  - openpi
  - pi0
  - robotics
  - simulation

WARP-RM paper simulation policy checkpoints

This repository contains the two model-only policy parameter trees used for the paper simulation comparison: the baseline policy and the WARP-RM RABC policy. It omits optimizer/train state and does not contain a redistributed training checkpoint.

The released directories are complete serving parameter trees when used with the public OpenPI code. Their redistribution and use remain subject to the applicable upstream OpenPI/Pi0 terms; this repository therefore uses the custom license setting rather than asserting an Apache-2.0 grant for upstream-derived model weights.

Layout:

vanilla/params/ and vanilla/assets/ are the baseline policy tree.
warp_rabc_sss15/params/ and warp_rabc_sss15/assets/ are the WARP-RM reward-aligned BC policy tree.

Pass either containing directory as the local policy checkpoint directory to the released OpenPI serving command. The assets/ directory is required; do not rename or discard it.

Files and SHA256 checksums are listed in MANIFEST.json.