GTAILGMAMLAug 17, 2020

Learning Game-Theoretic Models of Multiagent Trajectories Using Implicit Layers

arXiv:2008.07303v731 citations
Originality Incremental advance
AI Analysis

This work addresses trajectory prediction for multiagent systems like autonomous vehicles, offering an incremental improvement by integrating game theory with neural networks for better interpretability and transferability.

The paper tackles the problem of predicting interacting agents' trajectories by proposing an end-to-end trainable architecture that hybridizes neural networks with game-theoretic reasoning, achieving interpretable representations and transfer to decision-making tasks, with evaluation on real-world highway driver merging datasets.

For prediction of interacting agents' trajectories, we propose an end-to-end trainable architecture that hybridizes neural nets with game-theoretic reasoning, has interpretable intermediate representations, and transfers to downstream decision making. It uses a net that reveals preferences from the agents' past joint trajectory, and a differentiable implicit layer that maps these preferences to local Nash equilibria, forming the modes of the predicted future trajectory. Additionally, it learns an equilibrium refinement concept. For tractability, we introduce a new class of continuous potential games and an equilibrium-separating partition of the action space. We provide theoretical results for explicit gradients and soundness. In experiments, we evaluate our approach on two real-world data sets, where we predict highway driver merging trajectories, and on a simple decision-making transfer task.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes