Recent work has shown that deep reinforcement-learning agents can learn to follow language-like instructions from infrequent environment rewards. However, for many real-world natural language commands that involve a degree of underspecification or ambiguity, such as "tidy the room", it would be challenging or impossible to program an appropriate reward function. To overcome this, we present a method for learning to follow commands from a training set of instructions and corresponding example goal-states, rather than an explicit reward function. Importantly, the example goal-states are not seen at test time. The approach effectively separates the representation of what instructions require from how they can be executed.

Artificial intelligence, robots, and automation are rising in importance in many areas. As noted in the recent book, " The Future of Work: Robots, AI, and …

Advances in computer vision algorithms and the application of modern artificial intelligence (AI) techniques have made writing visual tests practical.

Outlining what automation, artificial intelligence and big data can do for air travel, the carrier's president Tim Clark laid out a vision in which robots, with …