Friday, December 13, 2019

VentureBeat: DeepMind proposes novel way to train 'safe' reinforcement learning AI


DeepMind proposes novel way to train 'safe' reinforcement learning AI
Reinforcement learning agents -- or AI that's progressively spurred toward goals via rewards (or punishments) -- form the foundation of self-driving cars, dexterous robots, and drug discovery systems. But because they're predisposed to explore unfamiliar states, they're susceptible to what's called the safe exploration problem, wherein they become fixated on unsafe states (like a mobile...

Read in VentureBeat: https://apple.news/AMS40dT_XROSJsral2SoerA


Shared from Apple News


_- Steve

No comments: