MA2RL: Masked Autoencoders For Generalizable Multi-agent Reinforcement Learning
2025 · Jinyuan Feng, Min Chen, Zhiqiang Pu, et al.
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 \textbf\{M\}asked \textbf\{A\}utoencoders for \textbf\{M\}ulti-\textbf\{A\}gent \textbf\{R\}einforcement \textbf\{L\}earning (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 actio
Authors
(none)
Tags
Stats
Related papers
- Masked Autoencoding For Scalable And Generalizable Decision Making (2022)0.00
- MAGIC-MASK: Multi-agent Guided Inter-agent Collaboration With Mask-based Explainability For Reinforcement Learning (2025)0.00
- Genai-based Multi-agent Reinforcement Learning Towards Distributed Agent Intelligence: A Generative-rl Agent Perspective (2025)0.00
- MA2QL: A Minimalist Approach To Fully Decentralized Multi-agent Reinforcement Learning (2022)0.00
- Skill-aware Mutual Information Optimisation For Generalisation In Reinforcement Learning (2024)0.00
- Multi-agent Reinforcement Learning: A Report On Challenges And Approaches (2018)0.00
- Scalable Multi-agent Inverse Reinforcement Learning Via Actor-attention-critic (2020)0.00
- Robustifying A Policy In Multi-agent RL With Diverse Cooperative Behaviors And Adversarial Style Sampling For Assistive Tasks (2024)0.00