SOURCE-LINKED INTELLIGENCE

Deep Bayesian Reinforcement Learning -- Unifying Perception, Planning, and Control

CORDIS · observation · Publication date unknown

lity to manipulate diverse objects is imperative. So far, however, robotic manipulation technology has struggled in managing the uncertainty and unstructuredness that characterize human environments. Machine learning is a natural approach -- the robot can adapt to a given scenario, even if it was not programmed to handle it beforehand. Indeed, Deep Reinforcement Learning (deep RL), which has recently led to AI breakthroughs in computer games, has been publicized as the learning-based approach to robotics. To date, however, deep RL studies focused on known and observable systems, where uncertainty was resolved by lengthy trial and error. Quickly learning to act in novel environments, as required for robotics, is not yet within our reach. The crux of the matter is the tight coupling between perception and control under high uncertainty -- the robot must actively reduce uncertainty while also trying to solve the task; for complex and high-dimensional systems, we do not have a suitable algorithmic framework for this. In this proposal, our overarching goal is to: Develop the algorithmic

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

1500000

unit

EUR