We propose a novel framework for multitask reinforcement learning which seeks to distill shared structure among tasks into a low-complexity representation, which is then leveraged to accelerate...

Both animals and artificial agents benefit from state representations that support rapid transfer of learning across tasks and which enable them to efficiently traverse their environments to reach...

Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be...

Colaboratory notebook