User:PhizzyWhizzy/sandbox

MuJoCo
Developer(s)	Emanuel Todorov
Stable release	1.5 / January 26, 2017; 7 years ago
Written in	C, C++
Operating system	Microsoft Windows, OS X, Linux
Type	Physics engine
License	Trialware, Proprietary Software

This is the user sandbox of PhizzyWhizzy. A user sandbox is a subpage of the user's user page. It serves as a testing spot and page development space for the user and is not an encyclopedia article. Create or edit your own sandbox here.

Other sandboxes: Main sandbox | Template sandbox

Finished writing a draft article? Are you ready to request review of it by an experienced editor for possible inclusion in Wikipedia? Submit your draft for review!

MuJoCo (Multi-Joint dynamics with Contact) is a physics engine designed to facilitate robot simulation and model-based optimisation. It was authored by Emanuel Todorov.

Features

According to the official website^[1], MuJoCo's main features are:

Simulation in generalized coordinates, avoiding joint violations.
Inverse dynamics that are well-defined even in the presence of contacts.
Unified continuous-time formulation of constraints via convex optimization.
Constraints include soft contacts, limits, dry friction, equality constraints.
Actuators including motors, cylinders, muscles, tendons, slider-cranks.
Choice of Newton, conjugate gradient, or Projected Gauss-Seidel solvers.
Choice of pyramidal or elliptic friction cones, dense or sparse matrices.
Choice of Euler or Runge-Kutta numerical integrators.
Multi-threaded sampling and finite-difference approximations.
Intuitive XML model format (called MJCF) and built-in model compiler.
Cross-platform GUI with interactive 3D visualization in OpenGL.
Run-time module written in ANSI C and hand-tuned for performance.

Projects using the engine

MuJoCo has been used by researchers in UC Berkley^[2], Google DeepMind,^[3] and openAI

References

^ ^a ^b ""Official Homepage"". Retrieved 9 July 2017.
^ Levine, Sergey; et al. (2016). "End-to-end training of deep visuomotor policies". Journal of Machine Learning Research. 17 (1): 1334–1373. {{cite journal}}: Explicit use of et al. in: |last2= (help)
^ Lillicrap, Timothy P.; et al. (2015). "Continuous control with deep reinforcement learning". arXiv:1509.02971. {{cite arXiv}}: Explicit use of et al. in: |first= (help)

External links

No URL found. Please specify a URL here or add one to Wikidata.

Category:Computer physics engines

[homepage-1] ""Official Homepage"". Retrieved 9 July 2017.

[2] Levine, Sergey; et al. (2016). "End-to-end training of deep visuomotor policies". Journal of Machine Learning Research. 17 (1): 1334–1373. {{cite journal}}: Explicit use of et al. in: |last2= (help)

[3] Lillicrap, Timothy P.; et al. (2015). "Continuous control with deep reinforcement learning". arXiv:1509.02971. {{cite arXiv}}: Explicit use of et al. in: |first= (help)

[1]

v t e Physics engines (list)
Game physics Procedural animation Physically based animation Ragdoll physics
Free / open source	Box2D Bullet Cannon.js Chipmunk Newton Game Dynamics Open Dynamics Engine OPAL Physics Abstraction Layer PhysX Phyz Project Chrono Siconos Simulation Open Framework Architecture Tokamak
Proprietary	AGX Multiphysics Algodoo Chipmunk Digital Molecular Matter Euphoria Havok Reactor Vortex
Related topics	Tire model