REINFORCEMENT LEARNING USING DISTRIBUTED PRIORITIZED REPLAY

Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. one of the systems includes (i) a plurality of actor computing units, in which each of the actor computing units is configured to maintain a respective replica of the action selection neural network and to perform a plurality of actor operations, and (ii) one or more learner computing units, in which each of the one or more learner computing units is configured to perform a plurality of learner operations.

Inventor(s): David Budden, Gabriel Barth-Maron, John Quan, Daniel George Horgan

CPC Classification: G06N3/08 (Learning methods)

Search for rejections for patent application number 20250217646