Can we design online interventions that will help humans achieve certain goals in such asynchronous setting? In this paper, we address the above problem from the perspective of deep reinforcement learning of marked temporal point processes, where both the actions taken by an agent and the feedback it receives from the environment are asynchronous stochastic discrete events characterized using marked temporal point processes. In doing so, we define the agent's policy using the intensity and mark distribution of the corresponding process and then derive a flexible policy gradient method, which embeds the agent's actions and the feedback it receives into real-valued vectors using deep recurrent neural networks. Our method does not make any assumptions on the functional form of the intensity and mark distribution of the feedback and it allows for arbitrarily complex reward functions. We apply our methodology to two different applications in viral marketing and personalized teaching and, using data gathered from Twitter and Duolingo, we show that it may be able to find interventions to help marketers and learners achieve their goals more effectively than alternatives.

TPP models in density estimation and strongly outperforms them in forecasting.

Learning continuous-time point processes is essential to many discrete event forecasting tasks.

There are plenty of previous studies targeting the problem from different aspects. For temporal point process, agreat number of works [3, 13, 15, 16, 28] attempt to model the intensify function from statistic views, and recent studies harness deep recurrent model [24], generative adversarial network [23] and reinforcement learning [19, 18] to learn the temporal process. These researches mainly focus on one-dimension eventsequences where eacheventpossesses thesame marker.

Neural Information Processing Systems http://nips.cc/

A temporal point process is a mathematical model for a time series of discrete events, which covers various applications. Recently, recurrent neural network (RNN) based models have been developed for point processes and have been found effective.

Thesemodels typically assume that all event sequences come from the same data distribution.

Machine learning models based on temporal point processes arethe state ofthe artinawide variety ofapplications involving discrete events incontinuous time.