Motivated Reinforcement Learning
Peter Dayan
NIPS 2001, to appear
Abstract
The standard reinforcement learning view of the involvement of
neuromodulatory systems in instrumental conditioning includes a
rather straightforward conception of motivation as prediction of sum
future reward. Competition between actions is based on the
motivating characteristics of their consequent states in this sense.
Substantial, careful, experiments reviewed in Dickinson \& Balleine
(1994l 2001) into the neurobiology and psychology of motivation
shows that this view is incomplete. In many cases, animals are
faced with the choice not between many different actions at a given
state, but rather whether a single response is worth executing at
all. Evidence suggests that the motivational process underlying this
choice has different psychological and neural properties from that
underlying action choice. We describe and model these motivational
systems, and consider the way they interact.
compressed postscript
pdf