Patent · US Active

Reinforcement learning using distributed prioritized replay

US11625604B2 · kind B2 · utility

2Cited by
0References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 29, 2018
Grant dateApr 11, 2023
Priority date
Expiry dateDec 10, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.