基于部分观测的多智能体相互作用的随机预测
Stochastic Prediction of Multi-Agent Interactions from Partial Observations
摘要:
我们提出了一种方法,学习整合时间信息,从一个学习的动态模型,模糊的视觉信息,从一个学习的视觉模型,在交互代理的上下文中。我们的方法基于图结构的变分递归神经网络(Graph-VRNN),该网络经过端到端训练,可以推断(部分观察到的)世界的当前状态,并预测未来状态。我们证明了我们的方法在两个体育数据集上的表现优于各种基线,一个是基于真实的篮球轨迹,另一个是由足球游戏引擎生成的。
英文摘要:
We present a method that learns to integrate temporal information, from a learned dynamics model, with ambiguous visual information, from a learned vision model, in the context of interacting agents. Our method is based on a graph-structured variational recurrent neural network (Graph-VRNN), which is trained end-to-end to infer the current state of the (partially observed) world, as well as to forecast future states. We show that our method outperforms various baselines on two sports datasets, one based on real basketball trajectories, and one generated by a soccer game engine.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。