2021
Continual Auxiliary Task Learning
Matthew K McLeod, Chunlok Lo, Matthew Kyle Schlegel, Andrew Jacobsen, Raksha Kumaraswamy, Martha White +1
NeurIPS 2021poster
Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there is little work on how to adapt the behavior to gather usefu…