Voting-Based Multiagent Reinforcement Learning for Intelligent IoT

doi:10.1109/JIOT.2020.3021017

Voting-Based Multiagent Reinforcement Learning for Intelligent IoT

2021-02-15

10

OA

AI

DOI：10.1109/JIOT.2020.3021017

Original

Save

View PDF

Abstract

En 中文

The recent success of single-agent reinforcement learning (RL) in Internet of Things (IoT) systems motivates the study of multiagent RL (MARL), which is more challenging but more useful in large-scale IoT. In this article, we consider a voting-based MARL problem, in which the agents vote to make group decisions and the goal is to maximize the globally averaged returns. To this end, we formulate the MARL problem based on the linear programming form of the policy optimization problem and propose a primal-dual algorithm to obtain the optimal solution. We also propose a voting mechanism through which the distributed learning achieves the same sublinear convergence rate as centralized learning. In other words, the distributed decision making does not slow down the process of achieving global consensus on optimality. Finally, we verify the convergence of our proposed algorithm with numerical simulations and conduct case studies in practical multiagent IoT systems.

Keywords:

Convergence

Internet of Things

Optimization

Collaboration

Task analysis

Learning (artificial intelligence)

Games

Multiagent reinforcement learning (MARL)

primal– dual algorithm

voting mechanism

Voting-Based Multiagent Reinforcement Learning for Intelligent IoT

Abstract

AI Summary

Journal

Organization