MA2RL: Masked Autoencoders for Generalizable Multi-Agent Reinforcement Learning
- 18 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (8) , 1-14
Abstract
To develop generalizable models in multi-agent reinforcement learning, recent approaches have been devoted to discovering task-independent skills for each agent, which generalize across tasks and facilitate agents’ cooperation. However, particularly in partially observed settings, such approaches struggle with sample efficiency and generalization capabilities due to two primary challenges: (a) How to incorporate global states into coordinating the skills of different agents? (b) How to learn generalizable and consistent skill semantics when each agent only receives partial observations? To address these challenges, we propose a framework called Masked Autoencoders for Multi-Agent Reinforcement Learning (MA2RL), which encourages agents to infer unobserved entities by reconstructing entity-states from the entity perspective. The entity perspective helps MA2RL generalize to diverse tasks with varying agent numbers and action spaces. Specifically, we treat local entity-observations as masked contexts of the global entity-states, and MA2RL can infer the latent representation of dynamically masked entities, facilitating the assignment of task-independent skills and the learning of skill semantics. Extensive experiments demonstrate that MA2RL achieves significant improvements relative to state-of-the-art approaches, demonstrating extraordinary performance, remarkable zero-shot generalization capabilities and advantageous transfer-ability.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62322316)
- Young Scientists Foundation of CSAA (CSAA-YSF2025-GNC-08)
- Open Fund of National Key Laboratory of Information Systems Engineering (6142101240203)
This publication has 31 references indexed in Scilit:
- Efficient Multitask Reinforcement Learning via Task-Specific Action CorrectionIEEE Transactions on Cognitive and Developmental Systems, 2025
- Multi-agent policy transfer via task relationship modelingScience China Information Sciences, 2024
- Enhancing Reinforcement Learning via Transformer-Based State Predictive RepresentationsIEEE Transactions on Artificial Intelligence, 2024
- Improving Generalization of Multi-agent Reinforcement Learning Through Domain-Invariant Feature Extraction2023
- Learning Visual Representation for Autonomous Drone Navigation via a Contrastive World ModelIEEE Transactions on Artificial Intelligence, 2023
- Sample Efficient Reinforcement Learning Using Graph-Based Memory ReconstructionIEEE Transactions on Artificial Intelligence, 2023
- Masked Autoencoders Are Scalable Vision Learners2022
- CSNAS: Contrastive Self-Supervised Learning Neural Architecture Search Via Sequential Model-Based OptimizationIEEE Transactions on Artificial Intelligence, 2021
- Neuroevolution in Deep Neural Networks: Current Trends and Future ChallengesIEEE Transactions on Artificial Intelligence, 2021
- A Concise Introduction to Decentralized POMDPs2016