公开(公告)号：US20230093451A1

公开(公告)日：2023-03-23

申请号：US17947985

申请日：2022-09-19

Applicant: Google LLC

Inventor： Robert Dadashi-Tazehozi ,  Olivier Claude Pietquin ,  Léonard Hussenot Desenonges ,  Matthieu Florent Geist ,  Anton Raichuk ,  Damien Vincent ,  Sertan Girgin

IPC: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. In particular, an agent can be controlled using a discretization neural network that generates a state-dependent discretization of an original action space and a policy neural network that is used to select an action from the state-dependent quantization rather than from the original action space.