← Search

Eugene Brevdo

2 accepted papers

2018

Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion

NeurIPS 2018oral

There is growing interest in combining model-free and model-based approaches in reinforcement learning with the goal of achieving the high performance of model-free algorithms with low sample complexity. This is difficult because an imperfect dynamics model can degrade the performance of the learnin…

2017

Deep Probabilistic Programming

ICLR 2017poster

We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations—random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationa…

Cited by 249SourceScholar