Skip to yearly menu bar Skip to main content


Poster

Small batch deep reinforcement learning

Johan Obando Ceron · Marc Bellemare · Pablo Samuel Castro

Great Hall & Hall B1+B2 (level 1) #1503

Abstract:

In value-based deep reinforcement learning with replay memories, the batch size parameter specifies how many transitions to sample for each gradient update. Although critical to the learning process, this value is typically not adjusted when proposing new algorithms. In this work we present a broad empirical study that suggests reducing the batch size can result in a number of significant performance gains; this is surprising, as the general tendency when training neural networks is towards larger batch sizes for improved performance. We complement our experimental findings with a set of empirical analyses towards better understanding this phenomenon.

Chat is not available.