# Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning

Oron AnschelNir BaramNahum Shimkin

Instability and variability of Deep Reinforcement Learning (DRL) algorithms tend to adversely affect their performance. Averaged-DQN is a simple extension to the DQN algorithm, based on averaging previously learned Q-values estimates, which leads to a more stable training procedure and improved performance by reducing approximation error variance in the target values... (read more)

PDF Abstract