chenlin/Mujoco_WASM
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

MuJoCo Warp documentation: Determinism.

Browse Source 
PiperOrigin-RevId: 840630917
Change-Id: Ie5f3ac34cee8812f20d6ae4fa6004385c5b048e0
This commit is contained in:
Taylor Howell
2025-12-05 02:07:07 -08:00
committed by Copybara-Service
parent fc109f0ab5
commit 4e84671a15
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/mjwarp/index.rst
+9
View File
@@ -418,6 +418,15 @@ for details and
`mjlab distributed training <https://github.com/mujocolab/mjlab/tree/main/docs/api/distributed_training.md>`__ for a
reinforcement learning example.
**Is MJWarp on GPU deterministic?**
No. There may be ordering or *small* numerical differences between results computed by different executions of the same
code. This is characteristic of non-deterministic atomic operations on GPU. Set device to CPU with
``wp.set_device("cpu")`` for deterministic results.
Developments for deterministic results on GPU are tracked in this
`GitHub issue <https://github.com/google-deepmind/mujoco_warp/issues/562>`__.
**How are orientations represented?**
Orientations are represented as unit quaternions and follow :ref:`MuJoCo's conventions<siLayout>`: