MuJoCo.org

Hive (and all of its expansions) has been added to OpenSpiel! 🎉🤩🐝🐜🕷️🐞🦟🪲

From Gen42: "Hive is an award-winning board game with a difference. There is no board. The pieces are added to the playing area thus creating the board. As more and more pieces are added the game becomes a fight to ...

🧵1/5

Architecting a Multi-Agent System with Google A2A and ADK How will you build AI systems with complex reasoning and distinct, specialized skills? Consider financial trading: success requires not…

Want to build AI agents on an architecture you can trust? Consider Google's ADK for self-contained agents, and A2A to connect your agents using an open protocol. Find out more:

📝 Blog post: medium.com/google-cloud...
⚙️ Code sample: github.com/kweinmeister...
🎬 Video: www.youtube.com/watch?v=EB-g...

Gemini Robotics

Our new Gemini Robotics model brings Gemini 2.0 to the physical world. It's our most advanced vision language action model, enabling robots that are interactive, dexterous, and general.

Learn more about how we're enabling the next generation of robotic AI agents at deepmind.google/robotics

This work wouldn’t have been possible without the most wonderful cast of collaborators from Berkeley, U. Toronto, Cambridge, Stanford and @deepmind.google.web.brid.gy.

MuJoCo Playground An open-source framework for GPU-accelerated robot learning and sim-to-real transfer

You can get started today
🌐 Project page: playground.mujoco.org
📂 Code: github.com/google-deepm...
📝 Paper: playground.mujoco.org/assets/playg...

playground.mujoco.org integrates high throughput batch rendering on GPU with Madrona-MJX. Using this, we trained a pixel-based block picking policy within minutes - achieving robust 100% success in real world trials.

With the Franka arm and playground.mujoco.org, we trained torque-controlled policies for contact-rich tasks like block reorientation. We obtain smooth, compliant and reactive behaviors running at 200Hz.

Locomotion is important, but what about the finer things in robotics? With playground.mujoco.org we took on the challenging task of dexterous in-hand reorientation with the open-source and low-cos LEAP hand. Our policy below was trained in 30 minutes on 2 4090s.

playground.mujoco.org allows humanoid robots to learn robust walking on different surfaces (below: Berkeley Humanoid, see other humanoid robots on the website).

playground.mujoco.org makes training locomotion policies straightforward and fast:
Quadrupeds like Go1: joystick control, fall recovery, handstands and footstands trained in minutes.

MuJoCo Playground An open-source framework for GPU-accelerated robot learning and sim-to-real transfer

The key to fast progress in robotics? Rapid iteration loops.
playground.mujoco.org streamlines the entire process from simulation to deployment and back.
In just 8 weeks, this unlocked:
- Zero-shot transfer across 5 robots.
- Locomotion, manipulation, and vision-based control.

MuJoCo Playground An open-source framework for GPU-accelerated robot learning and sim-to-real transfer

Introducing playground.mujoco.org
Combining MuJoCo’s rich and thriving ecosystem, massively parallel GPU-accelerated simulation, and real-world results across a diverse range of robot platforms: quadrupeds, humanoids, dexterous hands, and arms.
Get started today: pip install playground