DePAint: a decentralized safe multi-agent reinforcement learning algorithm considering peak and average constraints

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 54; no. 8; pp. 6108 - 6124
• Main Authors: Hassan, Raheeb, Wadith, K.M. Shadman, Rashid, Md. Mamun or, Khan, Md. Mosaddek
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-04-2024; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Automation; Collision avoidance; Computer Science; Constraints; Controllers; Machine learning; Machines; Manufacturing; Mechanical Engineering; Multiagent systems; Privacy; Processes; Resource management; Multi-agent reinforcement learning; Safe reinforcement learning; Peak constraint; Decentralized learning; Average constraint
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-024-05433-x

The domain of safe multi-agent reinforcement learning (MARL), despite its potential applications in areas ranging from drone delivery and vehicle automation to the development of zero-energy communities, remains relatively unexplored. The primary challenge involves training agents to learn optimal policies that maximize rewards while adhering to stringent safety constraints, all without the oversight of a central controller. These constraints are critical in a wide array of applications, including collision avoidance in autonomous systems, adherence to traffic and resource management laws in drone delivery, vehicle automation, and ensuring energy efficiency and sustainability in zero-energy communities. Moreover, ensuring the privacy of sensitive information in decentralized settings introduces an additional layer of complexity, necessitating innovative solutions that uphold privacy while achieving the system’s safety and efficiency goals. In this paper, we address the problem of multi-agent policy optimization in a decentralized setting, where agents communicate with their neighbors to maximize the sum of their cumulative rewards while also satisfying each agent’s safety constraints. We consider both peak and average constraints. In this scenario, there is no central controller coordinating the agents and both the rewards and constraints are only known to each agent locally/privately. We formulate the problem as a decentralized constrained multi-agent Markov Decision Problem and propose a momentum-based decentralized policy gradient method, DePAint, to solve it. To the best of our knowledge, this is the first privacy-preserving fully decentralized multi-agent reinforcement learning algorithm that considers both peak and average constraints. We then provide theoretical analysis and empirical evaluation of our algorithm in a number of scenarios and compare its performance to centralized algorithms that consider similar constraints.