VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement Learning
Qian Zhang, Zhuo Sun, Yao Zhang, Zhiwen Yu, Bin Guo, Jun Zhang

TL;DR
This paper introduces VIL2C, a communication scheme for multi-agent reinforcement learning that dynamically prioritizes important messages and adapts reception timing to reduce latency and improve performance in time-sensitive tasks.
Contribution
The paper proposes a novel VOI-based low-latency communication method with adaptive reception, providing theoretical performance guarantees and demonstrating superior results over existing approaches.
Findings
VIL2C improves MARL performance under various communication conditions.
The scheme effectively prioritizes high-VOI messages for low-latency transmission.
Adaptive reception reduces unnecessary waiting, enhancing system responsiveness.
Abstract
Inter-agent communication serves as an effective mechanism for enhancing performance in collaborative multi-agent reinforcement learning(MARL) systems. However, the inherent communication latency in practical systems induces both action decision delays and outdated information sharing, impeding MARL performance gains, particularly in time-critical applications like autonomous driving. In this work, we propose a Value-of-Information aware Low-latency Communication(VIL2C) scheme that proactively adjusts the latency distribution to mitigate its effects in MARL systems. Specifically, we define a Value of Information (VOI) metric to quantify the importance of delayed message transmission based on each delayed message's importance. Moreover, we propose a progressive message reception mechanism to adaptively adjust the reception duration based on received messages. We derive the optimized VoI…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsAge of Information Optimization · Reinforcement Learning in Robotics · Vehicular Ad Hoc Networks (VANETs)
