Patent · US Active

Training an unsupervised memory-based prediction system to learn compressed representations of an environment

US12159221B2 · kind B2 · utility

0Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 11, 2019
Grant dateDec 3, 2024
Priority date
Expiry dateDec 16, 2040

Classification

  • Technology area (CPC C)Chemistry; Metallurgy
  • CPC primaryC07C2601/14
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a memory-based prediction system configured to receive an input observation characterizing a state of an environment interacted with by an agent and to process the input observation and data read from a memory to update data stored in the memory and to generate a latent representation of the state of the environment. The method comprises: for each of a plurality of time steps: processing an observation for the time step and data read from the memory to: (i) update the data stored in the memory, and (ii) generate a latent representation of the current state of the environment as of the time step; and generating a predicted return that will be received by the agent as a result of interactions with the environment after the observation for the time step is received.

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