All the sessions from Transform 2021 are available on-demand now. DeepMind today detailed its latest efforts to create AI systems capable of completing a range of different, unique tasks. By designing a virtual environment called XLand, the Alphabet-backed lab says that it managed to train systems with the ability to succeed at problems and games including hide and seek, capture the flag, and finding objects, some of which they didn't encounter during training. The AI technique known as reinforcement learning has shown remarkable potential, enabling systems to learn to play games like chess, shogi, Go, and StarCraft II through a repetitive process of trial and error. But a lack of training data has been one of the major factors limiting reinforcement learning–trained systems' behavior being general enough to apply across diverse games.

There's much robots can achieve by observing human demonstrations, like the actions necessary to move a box of crackers from a counter to storage. But imitation learning is by no means a perfect science -- demonstrators often complete subgoals that distract systems from overarching tasks. To solve this, researchers at the University of Washington, Stanford University, the University of Illinois Urbana-Champaign, the University of Toronto, and Nvidia propose an "inverse planning" system that taps motions or low-level trajectories to capture the intention of actions. After evaluating their technique by collecting and testing against a corpus of video demonstrations conditioned on a set of kitchen goals, the team reports that their motion reasoning approach improves task success by over 20%. The researchers lay out the full extent of the problem in a preprint paper detailing their work.

Microsoft is using the video game Minecraft to help develop artificial intelligence (AI) which can complete complex tasks, and is opening up the research to the general computing public, according to a Monday announcement. Minecraft has been used by the tech company and several academic computer scientists to help develop sophisticated general artificial intelligence, or AI, which can do things like learn, hold conversations, make decisions and complete complex tasks. Microsoft has opened up the project to the general computing public via an open-source license. "Minecraft is very close to the real world in many ways," Jose Hernandez-Orallo, who is a professor at the Technical University of Valencia and has used the system to work on AI, wrote in a press statement. "There are so many possibilities."