Part of Advances in Neural Information Processing Systems 10 (NIPS 1997)
David Foster, Richard Morris, Peter Dayan
We provide a model of the standard watermaze task, and of a more challenging task involving novel platform locations, in which rats exhibit one-trial learning after a few days of training. The model uses hippocampal place cells to support reinforcement learning, and also, in an integrated manner, to build and use allocentric coordinates.