1 code implementation • 24 Nov 2022 • William Dorrell, Maria Yuffa, Peter Latham
Training data is always finite, making it unclear how to generalise to unseen situations.
1 code implementation • 30 Sep 2022 • William Dorrell, Peter E. Latham, Timothy E. J. Behrens, James C. R. Whittington
We suggest the brain must represent this consistent meaning of actions across space, as it allows you to find new short-cuts and navigate in unfamiliar settings.
no code implementations • 24 Jun 2020 • Sergio Verduzco-Flores, William Dorrell, Erik DeSchutter
We next show that in a more general case, neural reinforcement learning can be coupled with a feedback controller to reduce errors that arise non-monotonically from the control signal.