Voting-Based Multi-Agent Reinforcement Learning for Intelligent IoT
This work addresses the problem of efficient decision-making in multi-agent IoT systems, offering a distributed solution that maintains convergence speed, though it appears incremental as it builds on existing MARL and optimization methods.
The paper tackles the challenge of multi-agent reinforcement learning (MARL) in large-scale IoT systems by proposing a voting-based approach to maximize globally averaged returns, achieving a sublinear convergence rate comparable to centralized learning through a distributed primal-dual algorithm and verifying it with numerical simulations and case studies.
The recent success of single-agent reinforcement learning (RL) in Internet of things (IoT) systems motivates the study of multi-agent reinforcement learning (MARL), which is more challenging but more useful in large-scale IoT. In this paper, 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 distributed 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. Lastly, we verify the convergence of our proposed algorithm with numerical simulations and conduct case studies in practical multi-agent IoT systems.