XP-MARL: Auxiliary Prioritization in Multi-Agent Reinforcement Learning to Address Non-Stationarity

TL;DR

XP-MARL introduces an auxiliary prioritization framework in multi-agent reinforcement learning that stabilizes learning by learning priority policies and propagating actions, significantly improving safety in cooperative scenarios.

Contribution

The paper proposes XP-MARL, a novel framework that learns priority assignments and uses action propagation to address non-stationarity in cooperative MARL environments.

Findings

XP-MARL improves safety by 84.4% in CAV scenarios.

It outperforms state-of-the-art methods which improve baseline by 12.8%.

The approach stabilizes learning in multi-agent systems.

Abstract

Non-stationarity poses a fundamental challenge in Multi-Agent Reinforcement Learning (MARL), arising from agents simultaneously learning and altering their policies. This creates a non-stationary environment from the perspective of each individual agent, often leading to suboptimal or even unconverged learning outcomes. We propose an open-source framework named XP-MARL, which augments MARL with auxiliary prioritization to address this challenge in cooperative settings. XP-MARL is 1) founded upon our hypothesis that prioritizing agents and letting higher-priority agents establish their actions first would stabilize the learning process and thus mitigate non-stationarity and 2) enabled by our proposed mechanism called action propagation, where higher-priority agents act first and communicate their actions, providing a more stationary environment for others. Moreover, instead of using a predefined or heuristic priority assignment, XP-MARL learns priority-assignment policies with an auxiliary MARL problem, leading to a joint learning scheme. Experiments in a motion-planning scenario involving Connected and Automated Vehicles (CAVs) demonstrate that XP-MARL improves the safety of a baseline model by 84.4% and outperforms a state-of-the-art approach, which improves the baseline by only 12.8%. Code: github.com/cas-lab-munich/sigmarl