当前位置:
X-MOL 学术
›
arXiv.cs.GT
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Multiagent trajectory models via game theory and implicit layer-based learning
arXiv - CS - Computer Science and Game Theory Pub Date : 2020-08-17 , DOI: arxiv-2008.07303 Philipp Geiger, Christoph-Nikolas Straehle
arXiv - CS - Computer Science and Game Theory Pub Date : 2020-08-17 , DOI: arxiv-2008.07303 Philipp Geiger, Christoph-Nikolas Straehle
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
robust downstream decision making. It combines (1) a differentiable implicit
layer that maps preferences to local Nash equilibria with (2) a learned
equilibrium refinement concept and (3) a learned preference revelation net,
given initial trajectories as input. This is accompanied by a new class of
continuous potential games. We provide theoretical results for explicit
gradients and soundness, and several measures to ensure tractability. 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.
中文翻译:
基于博弈论和隐式层学习的多智能体轨迹模型
为了预测交互代理的轨迹,我们提出了一种端到端的可训练架构,该架构将神经网络与博弈论推理相结合,具有可解释的中间表示,并转移到稳健的下游决策。它结合了 (1) 将偏好映射到局部纳什均衡的可微隐层与 (2) 学习均衡细化概念和 (3) 学习偏好揭示网络,给定初始轨迹作为输入。这伴随着一类新的连续潜力游戏。我们提供了显式梯度和稳健性的理论结果,以及一些确保易处理性的措施。在实验中,我们在两个真实世界的数据集上评估我们的方法,其中我们预测高速公路司机合并轨迹,以及一个简单的决策转移任务。
更新日期:2020-09-18
中文翻译:
基于博弈论和隐式层学习的多智能体轨迹模型
为了预测交互代理的轨迹,我们提出了一种端到端的可训练架构,该架构将神经网络与博弈论推理相结合,具有可解释的中间表示,并转移到稳健的下游决策。它结合了 (1) 将偏好映射到局部纳什均衡的可微隐层与 (2) 学习均衡细化概念和 (3) 学习偏好揭示网络,给定初始轨迹作为输入。这伴随着一类新的连续潜力游戏。我们提供了显式梯度和稳健性的理论结果,以及一些确保易处理性的措施。在实验中,我们在两个真实世界的数据集上评估我们的方法,其中我们预测高速公路司机合并轨迹,以及一个简单的决策转移任务。