Files
Mujoco_WASM/mjx
Baruch Tabanpour bf04103b6f Import google-deepmind/mujoco_warp from GitHub.
#MIGRATION_3P_PY_MUJOCO_WARP__DEFAULT

  - 19dde09e179dbbaf4d07084185074f6a774b3255 update derivative.py by Taylor Howell <taylorhowell@google.com>
  - 04bc115c3766e974ef000cca16d40bacb92c01d2 fix _ray_hfield by Taylor Howell <taylorhowell@google.com>
  - 7fcbf8ddba08c9b9d33b0fdd4dd3fe39e40a0bd7 Use sparsity structures in `mjModel` rather than `mjData` by Yuval Tassa <6387526+yuvaltassa@users.noreply.github.com>
  - bfd2e4fe3cb5ba5dee97445ddc1d072344f443ec Fix override for enums (#617) by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - f4dbf5345bd5dcae60c415361dd425605b672e5c Add keyframe selection to viewer (#616) by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - 0e7edf9e8fd337502586929b2e4dd3d51201f462 add prunning to multiccd by Kyle Bayes <42924292+kbayes@users.noreply.github.com>
  - 791c30237cbdecf876bc53ac0b3dcff8b8b1317d format by Kyle Bayes <42924292+kbayes@users.noreply.github.com>
  - 7a7bae6c1390df3f29058e90f25f9ed5caab3fb1 Fix override in viewer and testspeed (#620) by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - 9e230c229c7dd721fbf6fa5fe69fc98717895500 add + 0.0 by Taylor Howell <taylorhowell@google.com>
  - 8a70a5e8839b84c11601bf1a98f9e7d1d31603f1 Update the test_cost unit test to test more properties (#... by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - cf317c60845b24ddba4b6814dbac9eba32b4c8b0 parallel linesearch with log scale for step sizes (#575) by Taylor Howell <taylorhowell@google.com>
  - b73e4edbc0d331d1e4f15c006d4535cc59595e70 add better reporting (#600) by adenzler-nvidia <116633880+adenzler-nvidia@users.noreply.github.com>
  - 007ad0b204ed4d48584024cce4676ac25a5695b5 Optimization: Fusing kernels around update_gradient_JTDAJ... by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - 640a89fcf452b9564508cacdeb30ecef3a83aede Adding static to broadphase filter (#621) by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - daca09ff3261db2713abc912191d6cf76437b8b7 Add reporting of converged worlds in testspeed (#619) by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - 33830bddd95a7f0d3febe1b090398ddadeb86ee2 Fix call to benchmark from asv (#627) by Kenny-Vilella <163487060+Kenny-Vilella@users.noreply.github.com>
  - 382eb65f7bb45798698f4025a980287ab1ec84c7 Update flex_bending dimensions (#628) by Alessio Quaglino <102665781+quagla@users.noreply.github.com>
  - c56b8875439cfaa93c1393f0a6e2ad057e029064 contact sensor maxforce reduction (#602) by Taylor Howell <taylorhowell@google.com>
  - 4f731941cb9dea397d4f71cf8151100b83eae576 A few airspeed velocity improvements. (#626) by Erik Frey <misc@fawx.com>

PiperOrigin-RevId: 797054114
Change-Id: I380e0b9446f94202b2389e2a760d6de5f0ec5af7
2025-08-19 16:01:28 -07:00
..
2025-01-23 02:51:51 -08:00

MuJoCo XLA (MJX)

PyPI Python Version PyPI version

This package is a re-implementation of the MuJoCo physics engine in JAX. This library is developed and maintained by Google DeepMind, and is kept up-to-date with the latest developments in MuJoCo itself.

The mujoco-mjx package is API-compatible with MuJoCo, but is missing some features found in MuJoCo. See our documentation for more details concerning feature parity.

Installation

The recommended way to install this package is via PyPI:

pip install mujoco-mjx

Usage

Once installed, the package can be imported via from mujoco import mjx. Please consult our documentation for further detail on the package's API.

We recommend going through the tutorial notebook which introduces the MJX API and trains a reinforcement learning policy in a few minutes: Open In
Colab

Versioning

The major.minor.micro portion of the version number matches the version of MuJoCo that this library provides. Optionally, if we release updates to MJX that target the same version of MuJoCo, a .postN suffix is added, for example 3.0.1.post2 represents the second update to MJX for MuJoCo 3.0.1.

License and Disclaimer

Copyright 2023 DeepMind Technologies Limited

MuJoCo and its libraries are licensed under the Apache License, Version 2.0. You may obtain a copy of the License at https://www.apache.org/licenses/LICENSE-2.0.

This is not an officially supported Google product.