Home Publications On the asymptotic equivalence between differential Hebbian and temporal difference learning
Personal tools

C Kolodziejski, B Porr, and F Wörgötter (2008)

On the asymptotic equivalence between differential Hebbian and temporal difference learning

Neural Computation in press.  (export entry)


Computational Neuroscience
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.