20th Century Fox

Google Has Started Adding Imagination to Its DeepMind AI

The robots have plans now.

DAVID NIELD
27 JUL 2017
 

Researchers have started developing artificial intelligence with imagination – AI that can reason through decisions and make plans for the future, without being bound by human instructions.

Another way to put it would be imagining the consequences of actions before taking them, something we take for granted but which is much harder for robots to do.

 

The team working at Google-owned lab DeepMind says this ability is going to be crucial in developing AI algorithms for the future, allowing systems to better adapt to changing conditions that they haven't been specifically programmed for. Insert your usual fears of a robot uprising here.

"When placing a glass on the edge of a table, for example, we will likely pause to consider how stable it is and whether it might fall," explain the researchers in a blog post. "On the basis of that imagined consequence we might readjust the glass to prevent it from falling and breaking." 

"If our algorithms are to develop equally sophisticated behaviours, they too must have the capability to 'imagine' and reason about the future. Beyond that they must be able to construct a plan using this knowledge."

We've already seen a version of this forward planning in the Go victories that DeepMind's bots have scored over human opponents recently, as the AI works out the future outcomes that will result from its current actions.

The rules of the real world are much more varied and complex than the rules of Go though, which is why the team has been working on a system that operates on another level.

To do this, the researchers combined several existing AI approaches together, including reinforcement learning (learning through trial and error) and deep learning (learning through processing vast amounts of data in a similar way to the human brain).

 

What they ended up with is a system that mixes trial-and-error with simulation capabilities, so bots can learn about their environment then think before they act.

One of the ways they tested the new algorithms was with a 1980s video game called Sokoban, in which players have to push crates around to solve puzzles. Some moves can make the level unsolvable, so advanced planning is needed, and the AI wasn't given the rules of the game beforehand.

The researchers found their new 'imaginative' AI solved 85 percent of the levels it was given, compared with 60 percent for AI agents using older approaches.

"The imagination-augmented agents outperform the imagination-less baselines considerably," say the researchers. "They learn with less experience and are able to deal with the imperfections in modelling the environment."

The team noted a number of improvements in the new bots: they could handle gaps in their knowledge better, they were better at picking out useful information for their simulations, and they could learn different strategies to make plans with.

It's not just advance planning – it's advance planning with extra creativity, so potential future actions can be combined together or mixed up in different ways in order to identify the most promising routes forward.

 

Despite the success of DeepMind's testing, it's still early days for the technology, and these games are still a long way from representing the complexity of the real world. Still, it's a promising start in developing AI that won't put a glass of water on a table if it's likely to spill over, plus all kinds of other, more useful scenarios.

"Further analysis and consideration is required to provide scalable solutions to rich model-based agents that can use their imaginations to reason about – and plan – for the future," conclude the researchers.

The researchers also created a video of the AI in action, which you can see below:

You can read the two papers published to the pre-print website arXiv.org here and here.

 

More From ScienceAlert

We really are born with a natural fear of spiders and snakes, new study shows

The arachnophobics among us are totally justified, thank you.

12 hours ago