Google’s DeepMind becomes ‘highly aggressive’ when stressed warns search giant
AI WARNING: Google’s DeepMind becomes ‘highly aggressive’
when stressed warns search giant
GOOGLE’S artificial intelligence program has learned to
become “aggressive” when it is in stressful situations, the search engine giant
has warned.
By SEAN MARTIN 10:47, Mon, Feb 13, 2017 | UPDATED: 11:54,
Mon, Feb 13, 2017
Despite numerous predictions from experts that AI could
lead to the downfall of humanity, including Stephen Hawking who claimed it
could be the “worst thing” for human beings, tech giants are continuing to
invest heavily in AI.
In 2016, Google’s AI program, known as DeepMind, showed
its makers it was capable of learning independently, teaching itself to beat
the world champion in a game of Go!.
Now, it has continued on its ruthless streak and opts for
“highly aggressive” strategies when it is in fear of losing.
In the latest tests, two DeepMind agents were tasked with
playing a game of ‘Gathering’ – a computer game where two people, or in this
case computers, play against each other to collect the most apples.
The AI beings operated smoothly when there were enough
apples to go around, but once the apples became more sparse, the DeepMind
systems began using laser beams, or tagging, to knock the other one out,
ensuring they could collect all the apples.
A blog post from the DeepMind team read: “We let the
agents play this game many thousands of times and let them learn how to behave
rationally using deep multi-agent reinforcement learning.
“Rather naturally, when there are enough apples in the
environment, the agents learn to peacefully coexist and collect as many apples
as they can.
“However, as the number of apples is reduced, the agents
learn that it may be better for them to tag the other agent to give themselves
time on their own to collect the scarce apples.”
Joel Z Leibo, who is part of the DeepMind team, told
Wired: "This model... shows that some aspects of human-like behaviour
emerge as a product of the environment and learning.
"Less aggressive policies emerge from learning in
relatively abundant environments with less possibility for costly action.
“The greed motivation reflects the temptation to take out
a rival and collect all the apples oneself.”
Comments
Post a Comment