Skip to yearly menu bar Skip to main content


Poster

Temporal-Difference Learning Using Distributed Error Signals

Jonas Guan · Shon Verch · Claas Voelcker · Ethan Jackson · Nicolas Papernot · William Cunningham

[ ]
Thu 12 Dec 4:30 p.m. PST — 7:30 p.m. PST

Abstract:

A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value predictions. However, dopamine is synchronously distributed in regionally homogeneous concentrations, which does not support explicit credit assignment (like used by backpropagation). It is unclear whether distributed errors alone are sufficient for synapses to make coordinated updates to learn complex, nonlinear reward-based learning tasks. We design a new deep Q-learning algorithm, Artificial Dopamine, to computationally demonstrate that synchronously distributed, per-layer TD errors may be sufficient to learn surprisingly complex RL tasks. We empirically evaluate our algorithm on MinAtar, the DeepMind Control Suite, and classic control tasks, and show it often achieves comparable performance to deep RL algorithms that use backpropagation.

Live content is unavailable. Log in and register to view live content