New intelligent system learns from simple problems to solve complex ones

February 9, 2018, Australian National University
Action Schema Networks (ASNets) could hypothetically enable a robot to learn to navigate a floor with 10 rooms, and then be able to roam on a floor with thousands of rooms. Credit: Australian National University

Researchers at The Australian National University (ANU) have designed a new type of intelligent system based on deep learning that can learn to solve decision-making problems, including problems more complex than it has been trained to solve.

Deep learning is a popular artificial intelligence technique for tasks such as creating captions to describe images, transcribing speech to text and learning how to play video or board games from images alone.

Lead researcher Sam Toyer said the system, called Action Schema Networks (ASNets), could hypothetically enable a robot to learn to navigate a floor with 10 rooms, and then be able to roam on a floor with thousands of rooms.

"ASNets' ability to solve much larger problems is a changer," said Mr Toyer, who developed ASNets as part of his thesis during his Bachelor of Advanced Computing (Research & Development) at ANU and was awarded a University Medal.

"Using our ASNet-based system, we could potentially create new cyber-security applications that find system vulnerabilities, or design new robotics software to perform specialised tasks in automated warehouses or unmanned space missions."

Mr Toyer said intelligent systems relied on automated planning technology to make decisions.

"Whether it's a Mars rover choosing where to take photos, or a smart grid deciding how to isolate a fault, you need a planning algorithm to choose the best course of action."

Mr Toyer said some deep learning-based systems, including AlphaGo, had been used to solve decision-making problems.

"AlphaGo, which achieved superhuman skill in the game of Go, is a recent and well-known example," he said.

"However, systems like AlphaGo can only play the game on a fixed board size.

"In contrast, ASNets can learn to solve problems of variable size. This allows them to quickly learn what they need to know on small, easy problems, then transfer that knowledge directly to much larger problems without re-training."

Co-researcher Dr. Felipe Trevizan from ANU and CSIRO's Data61 said ASNet did not compete against an adversary like AlphaGo does.

"Rather, it specialises in solving problems in dynamic and uncertain environments," he said.

Professor Sylvie Thiébaux, one of the ANU academics supervising Mr Toyer's thesis, said the research was a proof of concept, which could be further developed with industry to use in intelligent robotics to perform tasks autonomously in a wide range of settings.

She said the learnt how to play a game to arrange up to 35 blocks in a particular formation, having only been given 25 problems using up to nine blocks as part of its training.

"We gave ASNets a description of the game, some examples of plans for simple problems with a small number of blocks, and then it learnt to solve much more complex problems," said Professor Thiébaux from the ANU Research School of Computer Science.

Associate Professor Lexing Xie from the ANU Research School of Computer Science, who co-supervised Mr Toyer's thesis, said ASNets was a creative way to use .

"This work is the first to borrow designs for visual recognition to solve decision-making that look very different in nature, but share logical structures," she said.

Explore further: Where does AlphaGo go?

Related Stories

Where does AlphaGo go?

August 26, 2016

On March 15, 2016, Lee Sodol, an 18-time world champion of the ancient Chinese board game Go, was defeated by AlphaGo, a computer program. The event is one of the most historic in the field of artificial intelligence since ...

Startup to train robots like puppets

November 8, 2017

Robots today must be programmed by writing computer code, but imagine donning a VR headset and virtually guiding a robot through a task, like you would move the arms of a puppet, and then letting the robot take it from there.

Distinguishing between humans and computers in the game of go

November 6, 2017

(Phys.org)—By analyzing the statistical features of thousands of go games played by humans and computers, researchers have found that it's surprisingly easy to tell whether a game is being played by a human or by a computer. ...

Recommended for you

Cellular microRNA detection with miRacles

March 26, 2019

MicroRNAs (miRNAs) are short noncoding regulatory RNAs that can repress gene expression post-transcriptionally and are therefore increasingly used as biomarkers of disease. Detecting miRNAs can be arduous and expensive as ...

What happened before the Big Bang?

March 26, 2019

A team of scientists has proposed a powerful new test for inflation, the theory that the universe dramatically expanded in size in a fleeting fraction of a second right after the Big Bang. Their goal is to give insight into ...

Probiotic bacteria evolve inside mice's GI tracts

March 26, 2019

Probiotics—which are living bacteria taken to promote digestive health—can evolve once inside the body and have the potential to become less effective and sometimes even harmful, according to a new study from Washington ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.