Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

April 2009, Vol. 21, No. 4, Pages 1173-1202
(doi: 10.1162/neco.2008.04-08-750)
© 2008 Massachusetts Institute of Technology
On the Asymptotic Equivalence Between Differential Hebbian and Temporal Difference Learning
Article PDF (1.62 MB)
Abstract

In this theoretical contribution, we provide mathematical proof that two of the most important classes of network learning—correlation-based differential Hebbian learning and reward-based temporal difference learning—are asymptotically equivalent when timing the learning with a modulatory signal. This opens the opportunity to consistently reformulate most of the abstract reinforcement learning framework from a correlation-based perspective more closely related to the biophysics of neurons.