February 10, 2017
DeepMind, the London-based artificial intelligence unit of Google’s parent Alphabet Inc. has been running a series of simulations aimed at answering a key AI question once and for all: will the robots play nice, or will they try and kill us all?
DeepMind’s latest research is focused on the dichotomy between cooperation and competition, specifically among reward-optimized agents (human or synthetic), in highly variable environments.
The team is trying to expand the comfort zone of existing AI agents in a variety of ways, most recently through two distinct game types that draw heavily on elements from game theory.
In the first game, the two agents must compete to gather as many apples as possible, a straightforward premise centered around scarcity and cooperation. The more plentiful the apples, the more likely the players were to cooperate or, at least, leave the other alone.
The DeepMind team found that the greater the level of intelligence applied (or larger the neural network supporting the software agent), the more aggressive the software agents became.
This game rewarded cooperation (the complex behavior in this instance) far more than the apples game, regardless of how intelligent the participants were.
Leibo emphasized that in the current round of experiments, none of the software agents had a functioning short-term memory, and thus could not make inferences on other subjects’ behavior based on past experience.
“Going forward it would be interesting to equip agents with the ability to reason about other agent’s beliefs and goals,” he said.
This article was posted: Friday, February 10, 2017 at 8:18 am