ROBUST, SCALABLE AND GENERALIZABLE MACHINE LEARNING PARADIGM FOR MULTI-AGENT APPLICATIONS

Described is a learning system for multi-agent applications. In operation, the system initializes a plurality of learning agents. The learning agents include both tactical agents and strategic agents. The strategic agents take an observation from an environment and select one or more of the tactical...

Full description

Saved in:
Bibliographic Details
Main Authors Soleyman, Sean, Khosla, Deepak
Format Patent
LanguageEnglish
Published 10.09.2020
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Described is a learning system for multi-agent applications. In operation, the system initializes a plurality of learning agents. The learning agents include both tactical agents and strategic agents. The strategic agents take an observation from an environment and select one or more of the tactical agents to produce an action that is used to control a platform's actuators or simulated movements in the environment to complete a task. Alternatively, the tactical agents produce the action corresponding to a learned low-level behavior to control the platform's actuators or simulated movements in the environment to complete the task.
Bibliography:Application Number: US202016792869