Cocaine Signals Never Disappoint

Science's STKE  14 Dec 2004:
Vol. 2004, Issue 263, pp. tw451
DOI: 10.1126/stke.2632004tw451

The temporal difference reinforcement learning (TDRL) model provides a computational framework for describing how future rewards are valued, how current choices are made, and how differences between what is received and what is expected are fed back into updated calculations of future rewards. In TDRL, the difference signal between receipt and expectation is carried by neurons that use the transmitter dopamine. Redish (see the Perspective by Ahmed) applies this model and develops an explanation, in neural computational terms, for some aspects of behavior in the context of addictive substances. The key point is that cocaine induces, via pharmacologic pathways, a dopamine signal that does not accurately reflect or respond to the difference in actual and expected reward; cocaine is always valued as being more rewarding than originally thought.

A. D. Redish, Addiction as a computational process gone awry. Science 306, 1944-1947 (2004). [Abstract] [Full Text]

S. H. Ahmed, Addiction as compulsive reward prediction. Science 306, 1901-1902 (2004). [Summary] [Full Text]