Selective Experience Sharing in Reinforcement Learning Enhances Interference Management

TL;DR

This paper introduces a decentralized multi-agent reinforcement learning method that selectively shares experiences to effectively manage inter-cell interference, reducing communication overhead while maintaining high spectral efficiency.

Contribution

The paper presents a novel selective experience sharing approach in multi-agent RL for interference mitigation, improving efficiency and reducing communication costs.

Findings

Outperforms state-of-the-art decentralized multi-agent RL methods.

Achieves 98% of spectral efficiency with 75% less experience sharing.

Enables fully decentralized training and execution.

Abstract

We propose a novel multi-agent reinforcement learning (RL) approach for inter-cell interference mitigation, in which agents selectively share their experiences with other agents. Each base station is equipped with an agent, which receives signal-to-interference-plus-noise ratio from its own associated users. This information is used to evaluate and selectively share experiences with neighboring agents. The idea is that even a few pertinent experiences from other agents can lead to effective learning. This approach enables fully decentralized training and execution, minimizes information sharing between agents and significantly reduces communication overhead, which is typically the burden of interference management. The proposed method outperforms state-of-the-art multi-agent RL techniques where training is done in a decentralized manner. Furthermore, with a 75% reduction in experience sharing, the proposed algorithm achieves 98% of the spectral efficiency obtained by algorithms sharing all experiences.