论文标题
使用隐式层学习多动轨迹的游戏理论模型
Learning Game-Theoretic Models of Multiagent Trajectories Using Implicit Layers
论文作者
论文摘要
为了预测相互作用的代理的轨迹，我们提出了一种可端到端的训练架构，该体系结构将神经网与游戏理论推理融合在一起，具有可解释的中间表示形式，并转移到下游决策。它使用的网络揭示了代理商过去的联合轨迹的偏好，以及将这些偏好映射到局部NASH平衡的可区分隐式层，形成了预测的未来轨迹的模式。此外，它还学习了一个平衡的精致概念。为了进行障碍，我们引入了一类新的连续潜在游戏和动作空间平衡分离的分区。我们为明确的梯度和健全性提供理论结果。在实验中，我们评估了两个现实世界数据集的方法，即预测高速公路驱动程序合并轨迹以及简单的决策转移任务。
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.
