Aug 2026· Conference on Control Technology and Applications· pp. 418-423· 0 citations· 38 references
Abstract
Learning-enabled control systems increasingly rely on multi-agent reinforcement learning to operate in uncertain and interactive environments. While risk-aware decision-making has been shown to improve safety and robustness, deploying such algorithms on resource-constrained embedded platforms remains a significant challenge due to limited memory, compute, and communication resources. In this paper, we propose a risk-informed multi-agent reinforcement learning framework based on cumulative prospect theory (CPT) and introduce a CPT-SARSA algorithm suitable for real-time execution on low-power embedded hardware. We implement our algorithm on Arduino Nano 33 BLE Sense microcontrollers and evaluate real-time leader-follower coordination in a stochastic grid-world with obstacles and hazards. Our experiments show that CPT-informed agents achieve faster task completion and significantly fewer collisions compared to standard Q-learning, highlighting safety-efficiency tradeoffs under embedded constraints. This demonstration shows that complex multi-agent reinforcement learning algorithms can be deployed on low-cost commodity hardware, increasing access to state-of-the-art learning-enabled control without costly compute resources.
MA-PMBRL, a novel Multi-Agent Pessimistic Model-Based Reinforcement Learning framework for CAVs, incorporating a max-min optimization approach to enhance robustness and decision-making is proposed, demonstrating that the proposed framework represents a significant step toward scalable, efficient, and reliable multi-age...
Ruo-Qi Wen, Rong-Peng Li, Xing Xu et al.· IEEE Transactions on Mobile...· 1 citation
A graph-based safe multi-agent reinforcement learning (MARL) framework for cooperative navigation with time-varying topology is presented, integrating a attention-based actor and a Graph Attention Network (GAT) centralized critic, enabling scale-insensitive policy learning under time-varying communication topologies.
Sizhe Xiao, Li-Jing Dong, Rui-Ting Bai et al.· 0 citations
This paper develops a safe and fully decentralized multi-agent reinforcement learning (MARL) algorithm to solve a class of discrete-time control problems on networks, including the persistent monitoring problem. Fully decentralized control of agents, while offering numerous benefits, faces issues such as exponentially...
Unmanned surface and underwater vehicles face challenges in autonomously learning cooperative encirclement for high-value targets under partial observability, intermittent communication, and collision risks. This paper proposes a heterogeneous multi-agent reinforcement learning framework with safe decisionmaking. The f...
Feature-fusion Multi-Agent Proximal Policy Optimization (FMAPPO) is proposed, which fuses 2D LiDAR measurements with task-specific state information to enable safe decentralized multi-robot task assignment and navigation and demonstrates that the learned decentralized policies can coordinate multiple robots to service...
A. Abdalwhab, Giovanni Beltrame, David St-Onge· arXiv.org· 0 citations