The US military's secretive X-37B robot spaceplane blasted off from Florida on Thursday night on its seventh mission, the first launched atop a SpaceX Falcon Heavy rocket capable of delivering it to a higher orbit than ever before. The Falcon Heavy, composed of three liquid-fueled rocket cores strapped together, roared off its launch pad from NASA's Kennedy Space Center at Cape Canaveral in a spectacular liftoff carried live on a SpaceX webcast. The launch followed more than two weeks of false starts and delays attributed to poor weather and unspecified technical issues, leading ground crews to roll the spacecraft back to its hangar before proceeding with Thursday's flight. It came two weeks after China's own robot spaceplane, the Shenlong, or'Divine Dragon,' was launched on its third mission to orbit since 2020, adding a new twist to the growing US-Sino rivalry in space. The Pentagon has disclosed scant details about the X-37B mission, conducted by the US Space Force under the military's National Security Space Launch program.

Can we land a SpaceX Falcon Heavy Rocket in simulation using machine learning? Yes! Reinforcement learning is a technique that lets an agent learn how best to act in an environment using rewards as its signal. OpenAI released a library called Gym that lets us train AI agents really easily. We'll use a combination of the Tensorflow and gym libraries to build an RL agent capable of landing a rocket perfectly. The specific technique we're using is called proximal policy optimization, this is an actor-critic algorithm that is really popular.