Reinforcement Learning Journal, vol. TBD, 2025, pp. TBD.
Presented at the Reinforcement Learning Conference (RLC), Edmonton, Alberta, Canada, August 5–9, 2025.
Agent modeling is a critical component in developing effective policies within multi-agent systems, as it enables agents to form beliefs about the behaviors, intentions, and competencies of others. Many existing approaches assume access to other agents' episodic trajectories, a condition often unrealistic in real-world applications. Consequently, a practical agent modeling approach must learn a robust representation of the policies of the other agents based only on the local trajectory of the controlled agent. In this paper, we propose TransAM, a novel transformer-based agent modeling approach to encode local trajectories into an embedding space that effectively captures the policies of other agents. We evaluate the performance of the proposed method in cooperative, competitive, and mixed multi-agent environments. Extensive experimental results demonstrate that our approach generates strong policy representations, improves agent modeling, and leads to higher episodic returns.
Conor Wallace, Umer Siddique, and Yongcan Cao. "TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding." Reinforcement Learning Journal, vol. TBD, 2025, pp. TBD.
BibTeX:@article{wallace2025transam,
title={{TransAM}: {T}ransformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding},
author={Wallace, Conor and Siddique, Umer and Cao, Yongcan},
journal={Reinforcement Learning Journal},
year={2025}
}