.png){kind=icon}
.png){kind=icon}
Return
Robust model-based MARL via masked cross-agent completion under observation loss
.png){kind=icon}
PRE
AI
Z
M
J
R
董
DOI：10.1007/s11432-025-4808-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recent advances in model-based reinforcement learning (MBRL) have demonstrated potential for mitigating sample complexity in multi-agent reinforcement learning (MARL) through synthetic environment interaction generation. However, while conventional MBRL approaches typically assume agents maintain continuous observation access during inference, real-world implementations often face observation loss, where specific agents temporarily lose observational capabilities due to environmental interference or system failures. To deal with this challenge, we present RMIOv2, a novel model-based MARL framework that simultaneously delivers competitive performance in standard environments while maintaining robust decision-making capabilities under transient observation loss conditions. Specifically, RMIOv2 enhances the world model’s capability to consistently represent agent states through cross-agent Transformer fusion modules. Furthermore, RMIOv2 uses dynamic reward trend modeling to mitigate reward prediction errors. On the basis of this pre-training, the framework employs masked fine-tuning to improve the world model’s ability to reconstruct observations for agents experiencing observation loss, ensuring coordinated multi-agent decision-making. Our experiments demonstrate RMIOv2’s superiority over state-of-the-art approaches in both final performance after convergence and robustness to observation loss when handling agents experiencing observation loss.
Keywords:
world model
multi-agent reinforcement learning
model-based reinforcement learning
state reconstruction
Journal
IF:
7.6
Papers:
4.9K
Citations:
8.9K
Organization
Cited Papers