Papers for

internet of things developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Multi agent learning improves communication under tight data limits

Robust and Efficient Communication for Multi-Agent Learning

Abstract: Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messages are both informative and robust to physical constraints remains a significant challenge. This paper introduces Multi-Agent Regularized Communication (MARC), a novel framework inspired by information-theoretic principles of conditional mutual information. MARC employs an attention-based architecture coupled with a unique message regularization mechanism designed to minimize uncertainty regarding future system states, thereby inducing the learning of highly representative communication protocols. Crucially, we evaluate MARC under stringent communication bottlenecks and lossy channels, simulating the real-world constraints of autonomous robotic networks and decentralized systems. Our results demonstrate that MARC significantly outperforms state-of-the-art methods in complex cooperative domains. Furthermore, we provide a deep analysis of message characteristics, proving that MARC maintains high operational performance even under significant data compression, offering a scalable path for deploying intelligent agents in resource-constrained environments.

Mon 14 SeptMachine LearningArtificial IntelligenceMultiagent Systems
The gist
Communicating clearly is important when multiple intelligent agents work together, but it’s hard to send messages that are both useful and reliable when there isn’t much data to share or the network is noisy. The authors created a new approach called MARC that helps agents learn to send messages that reduce confusion about what will happen next. Their method uses attention mechanisms and special rules to make each message very informative and resilient. They showed that MARC works better than other methods when communication is limited or lossy, which is useful for robots and systems that operate under strict data constraints.
Open → 2609.15361v1

Self adaptive random access policy reduces network information delays

Self-Adaptive Threshold ALOHA

Abstract: We propose Self-Adaptive Threshold ALOHA (SATA), a distributed random-access policy to minimize the Age of Information (AoI). SATA uses 1-bit broadcast feedback and requires no explicit coordination or message passing among nodes. {We show that this minimal feedback is sufficient for each node to perfectly track the number of active users and adjust its access probabilities accordingly.} For any initial network state, SATA converges to a collision-free TDMA steady state in finite time whenever the age threshold satisfies $Γ\geq n$, where $n$ is the network size. We derive closed-form expressions for the long-term average AoI and throughput in steady state, and establish that, for $Γ=n$, the expected transient duration scales as $O(n\log n)$. Simulation results confirm that SATA closely approaches TDMA performance across a wide range of network sizes, significantly outperforming Slotted ALOHA, Threshold ALOHA, and 1-persistent Threshold Slotted ALOHA. Notably, the performance gap between SATA and the benchmark random-access policies becomes more pronounced as network size grows.

Sun 13 SeptNetworking and Internet Architecture
The gist
Networks often struggle to keep information fresh when many devices try to communicate at once. This paper presents Self-Adaptive Threshold ALOHA (SATA), a simple way for devices to take turns sending updates without needing detailed coordination. The authors show that SATA allows devices to quickly learn how many others are active and schedule their transmissions to avoid collisions. As a result, the system reaches a stable pattern that keeps delays low, performing close to ideal scheduling methods even as the network grows.
Open → 2609.14800v1