Timezone: »

Interaction Modeling with Multiplex Attention
Fan-Yun Sun · Isaac Kauvar · Ruohan Zhang · Jiachen Li · Mykel J Kochenderfer · Jiajun Wu · Nick Haber

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #409

Modeling multi-agent systems requires understanding how agents interact. Such systems are often difficult to model because they can involve a variety of types of interactions that layer together to drive rich social behavioral dynamics. Here we introduce a method for accurately modeling multi-agent systems. We present Interaction Modeling with Multiplex Attention (IMMA), a forward prediction model that uses a multiplex latent graph to represent multiple independent types of interactions and attention to account for relations of different strengths. We also introduce Progressive Layer Training, a training strategy for this architecture. We show that our approach outperforms state-of-the-art models in trajectory forecasting and relation inference, spanning three multi-agent scenarios: social navigation, cooperative task achievement, and team sports. We further demonstrate that our approach can improve zero-shot generalization and allows us to probe how different interactions impact agent behavior.

Author Information

Fan-Yun Sun (Stanford University)
Isaac Kauvar (Stanford University)
Ruohan Zhang (Stanford University)
Jiachen Li (Stanford University)
Mykel J Kochenderfer (Stanford University)
Jiajun Wu (Stanford University)
Nick Haber (Stanford University)

More from the Same Authors