Patent · US Active

Reinforcement learning using pseudo-counts

US11727264B2 · kind B2 · utility

1Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 18, 2017
Grant dateAug 15, 2023
Priority date
Expiry dateSep 5, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/092
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes obtaining data identifying (i) a first observation characterizing a first state of the environment, (ii) an action performed by the agent in response to the first observation, and (iii) an actual reward received resulting from the agent performing the action in response to the first observation; determining a pseudo-count for the first observation; determining an exploration reward bonus that incentivizes the agent to explore the environment from the pseudo-count for the first observation; generating a combined reward from the actual reward and the exploration reward bonus; and adjusting current values of the parameters of the neural network using the combined reward.

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