chenlin/Mujoco_WASM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

MuJoCo Warp documentation: Why are numerical results from MJWarp and MuJoCo different?.

Browse Source 
PiperOrigin-RevId: 853696967
Change-Id: I0cf8539e341d2aa1cfd07ac75de18128ce9beb3b
This commit is contained in:
Taylor Howell
2026-01-08 05:33:25 -08:00
committed by Copybara-Service
parent 765bd54c7c
commit ab939683bc
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/mjwarp/index.rst
+8
View File
@@ -498,6 +498,14 @@ size ``Data.nworld``. Some :class:`mjw.Model <mujoco_warp.Model>` fields having
Additionally, certain fields including ``Model.qM``, ``Data.efc.J``, and ``Data.efc.D`` are padded to enable fast Additionally, certain fields including ``Model.qM``, ``Data.efc.J``, and ``Data.efc.D`` are padded to enable fast
loading on GPU. loading on GPU.
**Why are numerical results from MJWarp and MuJoCo different?**
MJWarp utilizes `float <https://nvidia.github.io/warp/modules/functions.html#warp.float32>`__s in contrast to MuJoCo's
default double representation for :ref:`mjtNum`. Solver settings, including iterations, collision detection, and small
friction values may be sensitive to differences in floating point representation.
If you encounter unexpected results, including NaNs, please open a GitHub issue.
Compilation Compilation
----------- -----------