Agentformer: Agent-aware Transformers For Socio-temporal Multi-agent Forecasting

Abstract

Predicting accurate future trajectories of multiple agents is essential for autonomous systems, but is challenging due to the complex agent interaction and the uncertainty in each agent's future behavior. Forecasting multi-agent trajectories requires modeling two key dimensions: (1) time dimension, where we model the influence of past agent states over future states; (2) social dimension, where we model how the state of each agent affects others. Most prior methods model these two dimensions separately, e.g., first using a temporal model to summarize features over time for each agent independently and then modeling the interaction of the summarized features with a social model. This approach is suboptimal since independent feature encoding over either the time or social dimension can result in a loss of information. Instead, we would prefer a method that allows an agent's state at one time to directly affect another agent's state at a future time. To this end, we propose a new Transfor

Stats

• citations517
• S2 citations—
• github stars0
• HF likes0
• heat score20.36
• arxiv keyyuan2021agentformer

Related papers

• Transam: Transformer-based Agent Modeling For Multi-agent Systems Via Local Trajectory Encoding (2025)0.00
• Learning To Forecast Aleatoric And Epistemic Uncertainties Over Long Horizon Trajectories (2023)5.84
• Multi-agent Transformer-accelerated RL For Satisfaction Of STL Specifications (2024)0.00
• Prediction And Control With Temporal Segment Models (2017)0.00
• Episodic Future Thinking Mechanism For Multi-agent Reinforcement Learning (2024)0.00
• Models As Agents: Optimizing Multi-step Predictions Of Interactive Local Models In Model-based Multi-agent Reinforcement Learning (2023)6.77
• Multi Time Scale World Models (2023)2.51
• Relational Forward Models For Multi-agent Learning (2018)0.00