By optimizing reinforcement-learning algorithms, DeepMind uncovered new details about how dopamine helps the brain learn. By Karen Hao.
In 1951, Marvin Minsky, then a student at Harvard, borrowed observations from animal behavior to try to design an intelligent machine. At the time, neuroscientists had yet to figure out the mechanisms within the brain that allow animals to learn in this way.
In a paper published in Nature, DeepMind, Alphabet’s AI subsidiary, has once again used lessons from reinforcement learning to propose a new theory about the reward mechanisms within our brains.
At a high level, reinforcement learning follows the insight derived from Pavlov’s dogs: it’s possible to teach an agent to master complex, novel tasks through only positive and negative feedback.
It turns out the brain’s reward system works in much the same way—a discovery made in the 1990s, inspired by reinforcement-learning algorithms. Read more to learn the study outcomes!
[Read More]