CONTROLLING AGENTS USING LATENT PLANS

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes controlling the agent using a policy neural network that processes a policy input that includes (i) a current observation, (ii) a goal observation, an...

Full description

Saved in:
Bibliographic Details
Main Authors Zadeh, Seyed Mohammad Khansari, Lynch, Harrison Corey, Sermanet, Pierre
Format Patent
LanguageEnglish
Published 10.03.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes controlling the agent using a policy neural network that processes a policy input that includes (i) a current observation, (ii) a goal observation, and (iii) a selected latent plan to generate a current action output that defines an action to be performed in response to the current observation.
Bibliography:Application Number: US202017432366