Multi-Agent Distributed Reinforcement Learning for Making Decentralized Offloading Decisions

TL;DR

This paper introduces a decentralized multi-agent reinforcement learning framework for computation offloading, achieving significant improvements in system efficiency, resource utilization, and fairness in dynamic environments.

Contribution

It proposes a novel multi-agent online learning algorithm that handles partial, delayed, and noisy information, with a mechanism ensuring Nash equilibria for optimal resource allocation.

Findings

40% reduction in offloading failure rate

32% reduction in communication overhead

Up to 38% savings in computation resources

Abstract

We formulate computation offloading as a decentralized decision-making problem with autonomous agents. We design an interaction mechanism that incentivizes agents to align private and system goals by balancing between competition and cooperation. The mechanism provably has Nash equilibria with optimal resource allocation in the static case. For a dynamic environment, we propose a novel multi-agent online learning algorithm that learns with partial, delayed and noisy state information, and a reward signal that reduces information need to a great extent. Empirical results confirm that through learning, agents significantly improve both system and individual performance, e.g., 40% offloading failure rate reduction, 32% communication overhead reduction, up to 38% computation resource savings in low contention, 18% utilization increase with reduced load variation in high contention, and improvement in fairness. Results also confirm the algorithm's good convergence and generalization property in significantly different environments.