XP-MARL: Auxiliary Prioritization in Multi-Agent Reinforcement Learning to Address Non-Stationarity
Authors:
- Jianye XuJXJianye Xu
- Omar SobhyOSOmar Sobhy
- Bassam AlrifaeeBABassam Alrifaee
Preprint
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/sigmarlKeywords
All Related Versions
This publication has 9 references indexed in Scilit:
- SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning2024
- Deep Multi-Agent Reinforcement Learning for Highway On-Ramp Merging in Mixed TrafficIEEE Transactions on Intelligent Transportation Systems, 2023
- Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms2021
- Multiagent Reinforcement Learning: Rollout and Policy IterationIEEE/CAA Journal of Automatica Sinica, 2021
- Multi-Agent Reinforcement Learning Based Resource Management in MEC- and UAV-Assisted Vehicular NetworksIEEE Journal on Selected Areas in Communications, 2020
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- A survey and critique of multiagent deep reinforcement learningAutonomous Agents and Multi-Agent Systems, 2019
- Multiagent cooperation and competition with deep reinforcement learningPLOS ONE, 2017
- Multiagent Learning: Basics, Challenges, and ProspectsAI Magazine, 2012