Transam: Transformer-based Agent Modeling For Multi-agent Systems Via Local Trajectory Encoding

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywallace2025transam

Related papers

• Agentformer: Agent-aware Transformers For Socio-temporal Multi-agent Forecasting (2021)20.36
• Updet: Universal Multi-agent Reinforcement Learning Via Policy Decoupling With Transformers (2021)0.00
• Decentralized Transformers With Centralized Aggregation Are Sample-efficient Multi-agent World Models (2024)0.00
• Agent Modelling Under Partial Observability For Deep Reinforcement Learning (2020)0.00
• Learning Policy Representations In Multiagent Systems (2018)0.00
• Multi-agent Transformer-accelerated RL For Satisfaction Of STL Specifications (2024)0.00
• Models As Agents: Optimizing Multi-step Predictions Of Interactive Local Models In Model-based Multi-agent Reinforcement Learning (2023)6.77
• Learning Mixed Strategies In Trajectory Games (2022)0.00