Herke van Hoof

is this you? claim profile

0 followers
University of Amsterdam

Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement

The well-known Gumbel-Max trick for sampling from a categorical distribu...
03/14/2019 ∙ by Wouter Kool, et al. ∙ 10 ∙ share

read it
Policy Search with High-Dimensional Context Variables

Direct contextual policy search methods learn to improve policy paramete...
11/10/2016 ∙ by Voot Tangkaratt, et al. ∙ 0 ∙ share

read it
Addressing Function Approximation Error in Actor-Critic Methods

In value-based reinforcement learning methods such as deep Q-learning, f...
02/26/2018 ∙ by Scott Fujimoto, et al. ∙ 0 ∙ share

read it
BanditSum: Extractive Summarization as a Contextual Bandit

In this work, we propose a novel method for training neural networks to ...
09/25/2018 ∙ by Yue Dong, et al. ∙ 0 ∙ share

read it
Deep Generative Modeling of LiDAR Data

Building models capable of generating structured output is a key challen...
12/04/2018 ∙ by Lucas Caccia, et al. ∙ 0 ∙ share

read it
Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

Diversity of environments is a key challenge that causes learned robotic...
03/13/2019 ∙ by Sanjay Thakur, et al. ∙ 0 ∙ share

read it
Reinforcement Learning with Non-uniform State Representations for Adaptive Search

Efficient spatial exploration is a key aspect of search and rescue. In t...
06/15/2019 ∙ by Sandeep Manjanna, et al. ∙ 0 ∙ share

read it
Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales

Neural Network based controllers hold enormous potential to learn comple...
10/23/2019 ∙ by Sanjay Thakur, et al. ∙ 0 ∙ share

read it

Herke van Hoof

Featured Co-authors

Masashi Sugiyama

Max Welling

Aaron Courville

Joelle Pineau

Doina Precup

Jan Peters

Jackie Chi Kit Cheung

David Meger

Voot Tangkaratt

Gerhard Neumann

Gregory Dudek

Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement

Policy Search with High-Dimensional Context Variables

Addressing Function Approximation Error in Actor-Critic Methods

BanditSum: Extractive Summarization as a Contextual Bandit

Deep Generative Modeling of LiDAR Data

Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

Reinforcement Learning with Non-uniform State Representations for Adaptive Search

Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales