Google's deepmind create Al with an imagination

 Researchers of Google Deepmind have started developing Al with imagination. An algorithm  that can
reason through decisions and make plans for the future. In other words a system that can reason and imagine the consequence of an action before taking them.

As it is explained in deepmind blog post. "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, 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."

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.

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).

The trial and error system makes it possible for the bots to study their environment then think
before they act.

The proposed architectures was tested using 1980's  puzzle video game Called sokoban. The game involves the pushing of creates around to solve the puzzle. Advanced planning is needed, as some moves can the level unsolvable. The AI
solved 85 percent of the levels it was given,
compared with 60 percent for AI agents using
older approaches and
the AI wasn't given the rules of the game
beforehand.

Despite the success in testing the Al by the researchers of deepmind.  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.