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 …
R Yu, S Zheng, A Anandkumar, Y Yue - arXiv preprint arXiv:1711.00073, 2017 - arxiv.org
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 …
P Humbert, C Dubost, J Audiffren… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
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) …
T Liu - arXiv preprint arXiv:1808.03873, 2018 - arxiv.org
In the traditional framework of spectral learning of stochastic time series models, model parameters are estimated based on trajectories of fully recorded observations. However …