Want better AI? Try training it like a baby

By Paddy Smith
Share
Researchers at the Allen Institute for AI think letting AI play hide and seek allows for better learning for real-world scenarios...

Is AI training being done all wrong? Researchers at the Allen Institute for AI think that may be the case, and have put forward an alternative means of training machine learning algorithms – hide and seek.

What’s wrong with the way we train AI now?

Most AI training is done with tagged datasets (training data) or in virtual environments where research teams can avoid paying the additional expense of rent. However those virtual environments tend to be limited to a defined scope that fits the intended purpose of the AI.

So we should build a physical house for AI?

Of course not. The house remains virtual. You just make it bigger, more like a ‘sandbox’ environment in a video game. The Allen Institute set up a virtual environment invitingly dubbed AI2-THOR that has hundreds of flats containing virtual rooms – kitchens, bedrooms, bathrooms and so on.

Sounds nice. The AI must be happy there.

They are. The AI in the virtual environment have been given a game to play. It’s called Cache, though you may know it better as hide and seek. One AI hides something; the other has to find it.

Just like children do?

Exactly. And, just like small humans, the AI learn mapping, exploration, perspective, hiding, seeking and object manipulation. It’s a less 2D way of learning, and steepens the learning curve for robotics. The ‘bots get better at hiding and seeking.

But it takes 20 years to become an accountant?

Being an accountant is what computers can do at birth. What they can’t do easily is general intelligence, or artificial general intelligence (AGI), or – as we would – working stuff out on the fly. This project moves us a step close to AI that can start from nothing to build up an understanding of its environment.

With hide and seek?

With hide and seek. The researchers think using gameplay as a motivation can help AI to develop a whole new set of skills and usher in a new era of artificial intelligence.

Share

Featured Articles

Responsibility in the Age of AI: O’Reilly President Examines

O’Reilly President Laura Baldwin discusses the legal challenges unmitigated and unobserved use of Gen AI may present to enterprises

Schneider Electric Enhances AI Data Centre Operations

Schneider Electric teams with Nvidia to advance AI data centres, whilst emphasising global sustainability in energy management

How Can AI Firms Pay Publishers? Perplexity Has a Plan

AI search firm Perplexity extends its content licensing programme to 14 new media partners, offering revenue share and API access for publisher content

PwC and AWS Join Forces on Enterprise AI Controls System

AI Strategy

How Amazon Nova is Redefining AI for Enterprise Solutions

AI Strategy

MHP Study: AI Reshapes Global Auto Industry Trust Landscape

AI Strategy