Machines Are Developing Language Skills Inside Virtual Worlds

2 min read

Machines are learning to process simple commands by exploring 3-D virtual worlds.

Devices like Amazon’s Alexa and Google Home have brought voice-controlled technology into the mainstream, but these still only deal with simple commands. Making machines smart enough to handle a real conversation remains a very tough challenge. And it may be difficult to achieve without some grounding in the way the physical world works.

Attempts to solve this problem by hard-coding relationships between words and objects and actions requires endless rules, making a machine unable to adapt to new situations. And efforts to have machines learn about language for themselves normally require substantial human assistance.

Now teams at DeepMind, an AI-focused subsidiary of Alphabet, and Carnegie Mellon University have developed a way for machines to figure out simple principles of language for themselves inside 3-D environments based on first-person shooter computer games.

“Being able to do this in 3-D is definitely a significant step closer to being able to do it in the real world,” says Devendra Chaplot, a master’s student at CMU who will present his paper at the annual meeting of the Association for Computational Linguistics. The ultimate goal, he says, is creating a simulation so close to real life an AI trained in it can transfer what it learns into the real world.

Both the DeepMind and CMU approaches use deep reinforcement learning, popularized by DeepMind’s Atari-playing AI. A neural network is fed raw pixel data from a virtual environment and uses rewards, like points in a computer game, to learn by trial and error (see “10 Breakthrough Technologies 2017: Reinforcement Learning”).

Normally, the goal might be to achieve a high score inside the game, but here the two AI programs were given commands like “go to the green pillar” and then had to navigate to the correct object to receive rewards.

By running through millions of training scenarios at accelerated speeds, both AI programs learned to associate words with particular objects and characteristics, which let them follow the commands. They even learned to understand relational terms like “larger” or “smaller” to discriminate between similar objects.

Most important, both programs could “generalize” what they learned to unseen situations.

Continue Reading

Enjoyed this summary? Read the complete article at the source:

Continue at technologyreview.com →

Yves Mulkers

Yves Mulkers is the founder of 7wData and a widely followed voice in the data and AI community. He curates the 7wData and AI Beat newsletters, reaching hundreds of thousands of data and AI professionals, and writes on data strategy, analytics, AI, and the evolving data ecosystem.