We present Tensor-Train RNN (TT-RNN), a novel family of neural sequence architectures for
multivariate forecasting in environments with nonlinear dynamics. Long-term forecasting in …

Current reinforcement learning (RL) methods can successfully learn single tasks but often
generalize poorly to modest perturbations in task domain or training procedure. In this work …

We present Higher-Order Tensor RNN (HOT-RNN), a novel family of neural sequence
architectures for multivariate forecasting in environments with nonlinear dynamics. Long …

We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering
and prediction in dynamical systems. PSRNNs draw on insights from both Recurrent Neural …

This paper introduces an observational framework for measuring the effects of display
advertising. Causal measurement of display ad effects using observational data presents a …

Objective: In this paper, we present an original decision support algorithm to assist the
anesthesiologists delivery of drugs to maintain the optimal Depth of Anesthesia (DoA) …

Reinforcement Learning (RL) has emerged as the standard paradigm for sequential
decision-making and a framework for general intelligence. At its core, the RL problem is one …

The predictive representations hypothesis is that representing the state of the world in terms
of predictions about the future will result in good generalization. In this thesis, good …

Objective: In this paper, we present an original decision support algorithm to assist the
anesthesiologists delivery of drugs to maintain the optimal Depth of Anesthesia (DoA) …

In the traditional framework of spectral learning of stochastic time series models, model
parameters are estimated based on trajectories of fully recorded observations. However …