Large Motion Frame Interpolation
AI models can now continually learn from new data on intelligent edge devices like smartphones and sensors
New algorithms help four-legged robots run in the wild
Stretchy, bio-inspired synaptic transistor can enhance, weaken device memories
Active matter, curved spaces: Mini robots learn to ‘swim’ on stretchy surfaces
Fluidic circuits add analog options for controlling soft robots
Engineers discover new process for synthetic material growth, enabling soft robots that grow like plants
Quantization for Fast and Environmentally Sustainable Reinforcement Learning
Posted by Srivatsan Krishnan, Student Researcher, and Aleksandra Faust, Senior Staff Research Scientist, Google Research, Brain Team Deep reinforcement learning (RL) continues to make great strides in solving real-world sequential decision-making problems such as balloon navigation, nuclear physics, robotics, and…