OPTIMIZING POLICY CONTROLLERS FOR ROBOTIC AGENTS USING IMAGE EMBEDDINGS

There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of ima...

Full description

Saved in:
Bibliographic Details
Main Authors CHEBOTAR, YEVGEN, Sermanet, Pierre, Lynch, Harrison
Format Patent
LanguageEnglish
Published 18.05.2023
Subjects
CALCULATING
CHAMBERS PROVIDED WITH MANIPULATION DEVICES
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
CONTROL OR REGULATING SYSTEMS IN GENERAL
CONTROLLING
COUNTING
FUNCTIONAL ELEMENTS OF SUCH SYSTEMS
HAND TOOLS
MANIPULATORS
MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS
PERFORMING OPERATIONS
PHYSICS
PORTABLE POWER-DRIVEN TOOLS
REGULATING
TRANSPORTING
Online AccessGet full text

Cover

More Information
Summary:There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.
Bibliography:Application Number: US202318157919