TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911091779436544 |
|---|---|
| author | Wallace, Conor Siddique, Umer Cao, Yongcan |
| author_facet | Wallace, Conor Siddique, Umer Cao, Yongcan |
| contents | 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 \texttt{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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding Wallace, Conor Siddique, Umer Cao, Yongcan Multiagent Systems Artificial Intelligence 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 \texttt{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. |
| title | TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2508.02826 |