XAI-Guided Conservative Decentralized Execution for Offline Multi-Agent Network Slicing

2026-08-14

AI Summary

This study addresses the high interaction costs, safety risks, and deployment challenges associated with online multi-agent reinforcement learning (MARL) in network slice resource allocation. To overcome these limitations, this work proposes X-CODE, a framework integrating explainable AI with offline MARL. By leveraging explainability-aware reward shaping, X-CODE optimizes decentralized execution policies, enabling safe and efficient management without online interactions or inter-agent communication. Experimental results demonstrate that the proposed framework achieves zero resource conflicts during testing and reduces effective inference latency by 88%. Furthermore, it significantly decreases signaling overhead and slicing latency. These findings establish X-CODE as a secure, low-latency intelligent solution for dynamic network slicing environments, effectively bridging the gap between theoretical MARL models and practical, safety-critical telecommunications deployments.

Abstract

The recent advances toward sixth-generation (6G) and beyond-6G networks have accelerated the need for intelligent resource management mechanisms capable of supporting heterogeneous services under shared infrastructures in network slicing. However, resource allocation in network slicing naturally forms a resource-coupled cooperative optimization problem with competing slice demands. Slices compete for limited resources to minimize individual latencies while coordinating to avoid conflicts and underutilization. Although multi-agent reinforcement learning (MARL) has shown promising performance in such settings, existing online formulations remain costly, unsafe, and difficult to deploy due to their reliance on environmental interactions and communication among agents. In this work, we present explainable artificial intelligence (XAI)-guided conservative decentralized execution (X-CODE). X-CODE is an explainable offline MARL that operates offline without environmental interaction, nor inter-agent communication. It exploits explainability-aware reward shaping to modify the relative preference among joint offline transitions during centralized training to improve decentralized resource-allocation behavior. In deployment, the agents operate independently without signaling exchange among the agents. Simulation results demonstrate that the proposed approach achieves zero observed resource-conflict events in the evaluated test episodes while minimizing per-slice latencies. Moreover, the proposed framework exhibits lower signaling overhead and reduces effective inference latency by 88 % under the considered communication-delay model compared to the online baselines. Source codes and datasets are available through: https://github.com/Eslam211/xcode-ran-slicing.

Problem

• Network Slicing
• Multi-Agent Reinforcement Learning
• Resource Allocation
• Offline Learning
• Decentralized Execution

Innovation

• Offline MARL
• Explainable AI (XAI)
• Decentralized Execution
• Network Slicing
• Reward Shaping