Training an unsupervised memory-based prediction system to learn compressed representations of an environment
US12159221B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 11, 2019 |
| Grant date | Dec 3, 2024 |
| Priority date | — |
| Expiry date | Dec 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.