To avoid a bottleneck of bots, a team of MIT engineers is designing a kit of universal robotic parts that an astronaut could easily mix and match to rapidly configure different robot "species" to fit various missions on the moon. Once a mission is completed, a robot can be disassembled and its parts used to configure a new robot to meet a different task. The team calls the system WORMS, for the Walking Oligomeric Robotic Mobility System. The system's parts include worm-inspired robotic limbs that an astronaut can easily snap onto a base, and that work together as a walking robot. Depending on the mission, parts can be configured to build, for instance, large "pack" bots capable of carrying heavy solar panels up a hill.

A team of MIT engineers is designing a kit of universal robotic parts that an astronaut could easily mix and match to build different robot "species" to fit various missions on the moon. When astronauts begin to build a permanent base on the moon, as NASA plans to do in the coming years, they'll need help. Robots could potentially do the heavy lifting by laying cables, deploying solar panels, erecting communications towers, and building habitats. But if each robot is designed for a specific action or task, a moon base could become overrun by a zoo of machines, each with its own unique parts and protocols. To avoid a bottleneck of bots, a team of MIT engineers is designing a kit of universal robotic parts that an astronaut could easily mix and match to rapidly configure different robot "species" to fit various missions on the moon.

Menagerie is a collection of high-quality models for the MuJoCo physics engine, curated by DeepMind. A physics simulator is only as good as the model it is simulating, and in a powerful simulator like MuJoCo with many modeling options, it is easy to create "bad" models which do not behave as expected. The goal of this collection is to provide the community with a curated library of well-designed models that work well right out of the gate. Menagerie's only requirement is MuJoCo version 2.2.2 or higher. You can download prebuilt binaries from the GitHub releases page, or if you are working with Python, you can install the native bindings from PyPI via pip install mujoco 2.2.2.

Throughout scientific history, overarching theoretical frameworks have allowed researchers to grow beyond personal intuitions and culturally biased theories. They allow to verify and replicate existing findings, and to link is connected results. The notion of self-play, albeit often cited in multiagent Reinforcement Learning, has never been grounded in a formal model. We present a formalized framework, with clearly defined assumptions, which encapsulates the meaning of self-play as abstracted from various existing self-play algorithms. This framework is framed as an approximation to a theoretical solution concept for multiagent training. On a simple environment, we qualitatively measure how well a subset of the captured self-play methods approximate this solution when paired with the famous PPO algorithm. We also provide insights on interpreting quantitative metrics of performance for self-play training. Our results indicate that, throughout training, various self-play definitions exhibit cyclic policy evolutions.

When Abby Beckley started work on a salmon fishing boat in Alaska, worms were not high on her list of concerns. But it wasn't long before the 26-year-old woman became aware of something irritating her left eye. After several days, she finally went digging with her fingers… and plucked out a tiny worm. "I was just pulling them out, so I knew there were a lot," Beckley recently told National Geographic. Mystified, Beckley's doctors sent a sample of the errant worms to the state health department, who forwarded it to Richard Bradbury, a parasitologist at the Centers for Disease Control and Prevention's Parasitic Diseases Reference Laboratory, which identifies thousands of parasites every year that are too rare for doctors to recognize.