Skip to yearly menu bar Skip to main content


Oral

The Dormant Neuron Phenomenon in Deep Reinforcement Learning

Ghada Sokar · Rishabh Agarwal · Pablo Samuel Castro · Utku Evci

Ballroom C

Abstract:

In this work we identify the dormant neuron phenomenon in deep reinforcement learning, where an agent's network suffers from an increasing number of inactive neurons, thereby affecting network expressivity. We demonstrate the presence of this phenomenon across a variety of algorithms and environments, and highlight its effect on learning. To address this issue, we propose a simple and effective method (ReDo) that Recycles Dormant neurons throughout training. Our experiments demonstrate that ReDo maintains the expressive power of networks by reducing the number of dormant neurons and results in improved performance.

Chat is not available.