Google teaches its AI to DREAM: Firm hopes technique used by animals (including us) could boost learning speed
- Google taught its AI to dream similar that of animals to improve learning
- The system replays sequences of a game containing rewarding events
- Researchers also pulled inspiration from how babies learn motor skills
- It learned how actions affect what it see rather than just predictions
- This means the AI doesn't need to be customized to different games
Google's AI achieved record scores playing Atari and beat a human during a game of Go – but to do so, the system needed constant training over a long period of time.
In order to speed up and simplify the learning process, the team at DeepMind has now taught its AI to dream in a way that is similar to animals.
After replaying sequences of a game containing rewarding events, the system proved to learn the stages 10 times faster than previous algorithms.
Scroll down for videos
To speed up the learning process, the team at DeepMind has now taught its AI to dream in a way that is similar to animals. After the system began 'dreaming' about a game called Labyrinth (pictured), it proved to learn the stages 10x faster than the previous algorithms
After testing its agent, DeepMind found that its system, named Unsupervised Reinforcement and Auxiliary Learning agent (Unreal), can also play the game at 87 percent the performance of expert human players, reports ZDNet.
Researchers said now that they do not have to spend so much time training Unreal, they can carry on with more of their own experiments.
Unreal's dreams of chasing apples through a maze is the focus on the virtual game Labyrinth, which is similar to the popular video game series Quake.
The machine quickly walks through a windy maze and scores points every time it collects an apple in its path.
Researchers chose this game because it reinforces positive behavior with points and the system only knows part of the maze at a time – allowing them to monitor how fast it picks up the rest.
DeepMind researchers recently published a paper entitled 'Reinforcement Learning with Unsupervised Auxiliary Tasks', which highlights the 'dreaming' technique that improved the learning speed and final performance of the system.
And to do this, the team augmented the system with two main additional tasks – one mimics how babies develop motor skills and the other is similar to how animals dream.
The first task taught the AI to control pixels on the screen, which emphasizes learning how your actions affect what you will see rather than just predictions, which is similar to how a baby develops motor skills
'Just as animals dream about positively- or negatively-rewarding events more frequently, our agents preferentially replay sequences containing rewarding events,' they write in the paper.
The first task taught the AI to control pixels on the screen, which 'emphasizes learning how your actions affect what you will see rather than just predictions,' DeepMind explains in a blog post.
'This is similar to how a baby might learn to control their hands by moving them and observing the movements.'
Google's AI achieved record scores playing Atari and beat a human during a game of Go – but to do so, the system needed constant training over a long period of time. However, researchers have taught it to 'dream' about a game in order to enhance its performance
'By learning to change different parts of the screen, our agent learns features of the visual input that are useful for playing the game and getting higher scores.'
The second task taught Unreal to focus visual features in the game, which it has seen during previous rounds –allowing it to find shortcuts.
'The agent is trained to predict the onset of immediate rewards from a short historical context,' DeepMind explains.
'To better deal with the scenario where rewards are rare, we present the agent with past rewarding and non-rewarding histories in equal proportion.'
The second task taught Unreal to focus visual features in the game, which it has seen during previous rounds –allowing it to find shortcuts. 'The agent is trained to predict the onset of immediate rewards from a short historical context
'By learning on rewarding histories much more frequently, the agent can discover visual features predictive of reward much faster.'
Using these techniques, researchers found the AI was able to complete 57 Atari games and reach 13 levels during Labyrinth.
The team explains that their work isn't to just design a system that can master video games, but develop one that does need to be programmed to learn different games.
DeepMind says that their 'primary mission' is for the AI to 'learn to solve any complex problem without needing to be taught how'.
Most watched News videos
- Moment carer is caught on camera manhandling a dementia patient
- Ministry of Defence release build up to Marine A shooting Taliban fighter
- Woman filmed performing sex act in Florida court house
- Sky News presenter accidentally says 'pr**k' in Trump segment
- John Berocw says there's 'no issue' with baby being in commons
- Moments after Audi R8 GT crashes after driving almost 200 mph
- Ivanka posts video of Arabella singing a song for Chinese New Year
- MoD video shows build-up to moment marine shoots Taliban fighter
- Man hanging from windowsill of high flat falls to his death
- 'I'd like you to apologise': Moment outraged caller phones LBC
- Junkie holds young girl at knifepoint as he demands drugs from police
- Hilarious reactions by Swedes confronted with ten-metre dive
- EXCLUSIVE: Trump's Supreme Court pick Neil Gorsuch...
- Brought to tears by Sharia justice: Woman is forced to...
- Woman gives birth to 'FROG' baby in Zimbabwe… and is made...
- EXCLUSIVE: With frostbite on her hands and hair frozen to...
- 'WAKE UP & JOIN THE RESISTANCE': Sarah Silverman calls...
- Bupa carer is caught on hidden camera manhandling...
- Rotherham child sex gang shout 'Allahu Akbar' in court as...
- EXCLUSIVE PHOTOS Home sweet home! Neighbors welcome the...
- Anna Nicole's daughter Dannielynn shows off her wonderful...
- Mother reveals daughter, 13, 'was relentlessly bullied at...
- Trump HUNG UP on Australian PM after 'yelling' at him...
- Russian girl, 12, is raped by family friend before being...