US 2024/0256885 A1 · EXPLORATION METHOD BASED ON REWARD DECOMPOSITION IN MULTI-AGENT REINFORCEMENT LEARNING

Abstract

Provided is an exploration method based on reward decomposition in multi-agent reinforcement learning. The exploration method includes: generating a positive reward estimation model through neural network training based on training data including states of all agents, actions of all the agents, and a global reward true value; generating, for each of the agents, a first individual utility function based on the global reward true value and generating a second individual utility function using the positive reward estimation model; and determining an action of each of the agents using the first individual utility function and the second individual utility function based on the state of each of the agents.

Claims12

Dependent claims

An exploration method based on reward decomposition in multi-agent reinforcement learning, the exploration method comprising:

generating a positive reward estimation model through neural network training based on training data including states of all agents, actions of all the agents, and a global reward true value;
generating, for each of the agents, a first individual utility function based on the global reward true value and generating a second individual utility function using the positive reward estimation model;
and
determining an action of each of the agents using the first individual utility function and the second individual utility function based on the state of each of the agents.

1 more element

A computer system comprising:

a memory in which instructions readable by a computer are stored;
and
at least one processor implemented to execute the instructions,
wherein the at least one processor is configured to execute the instructions to:
generate a positive reward estimation model through neural network training based on training data including states of all agents, actions of all the agents, and a global reward true value;
generate, for each of the agents, a first individual utility function based on the global reward true value and generating a second individual utility function using the positive reward estimation model;
and
determine an action of each of the agents using the first individual utility function and the second individual utility function based on the state of each of the agents.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application

18/517,931Filed 22 Nov 2023

Priority

KR 10-2023-001007126 Jan 2023

Published

1 Aug 2024

Term ends

Not estimatedThe source records don’t support an estimate.

Classification6 codes

G06N 3/092
Learning methods: reinforcement learning
G06N 3/006
Artificial life, i.e. computing arrangements simulating life: based on simulated virtual individual or collective life forms, e.g. social…
G06N 3/045
Architecture, e.g. interconnection topology: combinations of networks
G06N 3/08
Neural networks: learning methods

Exploration method based on reward decomposition in multi-agent reinforcement learning

Life of this patent

Exploration method based on reward decomposition in multi-agent reinforcement learning

Life of this patent

Abstract

Claims12