Baidu’s AI team taught a virtual agent just like a human would their baby
Baidus artificial intelligence research team has achieved a significant milestone: teaching a virtual agent living in a 2D environment how to navigate its world using natural language commands, by first teaching it language through positive and negative reinforcement. The especially exciting thing, according to the scientists, is that the agent ended up developing a zero-shot learning ability, which essentiallymeans that the AI agent developed a basic sense of grammar.
You probably dont remember it from personal experience because it happened when you were a baby, but this is basically how parents teach their kids when very young. You show them images, repeat words and, eventually, with enough positive reinforcement, the kid can associate those words with those images and voil it knows the names of things.
Baidus big breakthrough, though, is that the agent within its system can apply to new situations commands its learned computers arent great at taking knowledge acquired before and applying it to new things. Heres the explanation direct from Baidus own research team of why and how its system is different:
Applying past knowledge to a newtaskis very easy for humansbut still difficult for current end-to-end learning machines. Althoughmachines mayknow what a dragon fruit lookslike, they cantperform the task cutthe dragon fruitwitha knife unless theyhave beenexplicitly trained with the datasetcontaining thiscommand.By contrast, our agent demonstrated the ability to transfer what theyknewabout the visual appearance ofadragon fruit as well as the task of cutXwitha knife successfully, without explicitly being trained to perform cut the dragon fruit with a knife.
The ability to generalize use of a skill used previously is no small feat for artificial intelligences. Its a model that shows systems can learn and apply retained knowledge in a manner similar to humans, even if only in the limited realm of a simplistic, video game-like 2D environment. Which is very unlike me, in fact: Ill never learn.