← Search

Nguyen-Tuong Duy

2 accepted papers

2020

Adaptive Discretization for Evaluation of Probabilistic Cost Functions

AISTATS 2020poster

In many real-world planning applications, e.g. dynamic design of experiments, autonomous driving and robot manipulation, it is necessary to evaluate candidate movement paths with respect to a safety cost function. Here, the continuous candidate paths need to be discretized first and, subsequently, e…

Cited by 2SourcePDFScholar
2018

Probabilistic Recurrent State-Space Models

ICML 2018oral

State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g., LSTMs) proved extremely successful in modeling complex time series data. Fully probabilistic SSMs, however, are often found har…