Rein Houthooft

PhD Researcher at Ghent Universityimec
in artificial intelligence & machine learning


After graduating summa cum laude from Ghent University (Belgium, EU) in 2014 with an engineering degree (burgerlijk ingenieur) in computer science, I obtained a PhD in 2017 (expected), advised by Filip De Turck. During my doctoral studies, I also acted as a researcher at the R&D institute imec. Initially I focused on the design of a experimental routing strategies for computer networks, but later my interests shifted to artificial intelligence and machine learning, which became my true passion.

More specifically, I focused on combining deep neural networks with structured prediction through graphical models. In collaboration with Case New Holland (CNH) Industrial, this research was applied to semantic segmentation for visual perception in autonomous vehicles. Later, my work focused on the study of exploration strategies for deep reinforcement learning. My PhD research was supported by a Doctoral Fellowship of the Research Foundation — Flanders (FWO) for fundamental research.

During my PhD studies, I performed research both at OpenAI and at the Berkeley Artificial Intelligence Research lab (BAIR), part of UC Berkeley, with Pieter Abbeel. This latter stay was supported by a Travel Grant of the FWO. In the beginning of 2017, I will join OpenAI full-time as a research scientist in machine learning.


Deep Reinforcement Learning and Generative Models

Reinforcement learning (RL) using nonlinear function approximators with a focus on continuous control tasks such as robot locomotion. In particular, the goal is to investigate how to achieve efficient exploration in deep RL through curiosity.

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Deep Reinforcement Learning Workshop at NIPS, 2016
H. Tang, R. Houthooft, D. Foote, A. Stooke, X. Chen, Y. Duan, J. Schulman, F. De Turck, P. Abbeel
VIME: Variational Information Maximizing Exploration
Advances in Neural Information Processing Systems (NIPS), 2016
R. Houthooft, X. Chen, Y. Duan, J. Schulman, F. De Turck, P. Abbeel
bibtexpdfgithub blog post spotlight video
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
Advances in Neural Information Processing Systems (NIPS), 2016
X. Chen, Y. Duan, R. Houthooft, J. Schulman, I. Sutskever, P. Abbeel
bibtexpdfgithub blog post
Benchmarking Deep Reinforcement Learning for Continuous Control
International Conference on Machine Learning (ICML), 2016
Y. Duan, X. Chen, R. Houthooft, J. Schulman, P. Abbeel

Structured Prediction and Deep Learning

Research into structured prediction models: in particular the goal is to blend structured prediction and deep learning techniques, with a focus on semantic image segmentation tasks in autonomous vehicles. This work was performed in collaboration with Case New Holland (CNH) Industrial; vehicle controller patent applications have been filed.

Integrated Inference and Learning of Neural Factors in Structural Support Vector Machines
Pattern Recognition, vol. 59, 2016
R. Houthooft, F. De Turck
Structured Output Prediction for Semantic Perception in Autonomous Vehicles
The 30th AAAI Conference on Artificial Intelligence (AAAI), 2016
R. Houthooft, C. De Boom, S. Verstichel, F. Ongenae, F. De Turck

Artificial Intelligence in Healthcare

Investigating the application of machine learning methods to medical data in order to extract relevant patient information. This work is performed in collaboration with the Laboratory of Intensive Care Outcomes Research of the Ghent University Hospital.

Random Survival Forests for Predicting the Bed Occupancy in the Intensive Care Unit
Computational and Mathematical Methods in Medicine, 2016
J. Ruyssinck, J. van der Herten, R. Houthooft, F. Ongenae, I. Couckuyt, B. Gadeyne, K. Colpaert, J. Decruyenaere, F. De Turck, T. Dhaene
Predictive Modelling of Survival and Length of Stay in Critically Ill Patients using Sequential Organ Failure Scores
Artificial Intelligence in Medicine, vol. 63, no. 3, 2015
R. Houthooft, J. Ruyssinck, J. van der Herten, S. Stijven, I. Couckuyt, B. Gadeyne, F. Ongenae, K. Colpaert, J. Decruyenaere, T. Dhaene, F. De Turck

Geometric Routing

My first research focused on building a novel routing algorithm called Forest Routing. By using graph embeddings in mathematical spaces, it has high scalability as well as native load balancing behavior. A coherent write-up on the subject can be found in my Master's thesis "Adaptive Geometric Routing for the Internet Backbone". Below, a demonstration of the developed model is shown.

Optimizing Robustness in Geometric Routing via Embedding Redundancy and Regeneration
Networks, vol. 66, no. 4, 2015
R. Houthooft, S. Sahhaf, W. Tavernier, F. De Turck, D. Colle, M. Pickavet
Robust Geometric Forest Routing with Tunable Load Balancing
The 34th Annual IEEE International Conference on Computer Communications (INFOCOM), 2015
R. Houthooft, S. Sahhaf, W. Tavernier, F. De Turck, D. Colle, M. Pickavet
Fault-Tolerant Greedy Forest Routing for Complex Networks
The 6th International Workshop on Reliable Networks Design and Modeling (RNDM), 2014 — best paper award
Featured in Global Communications Newsletter May 2015
R. Houthooft, S. Sahhaf, W. Tavernier, F. De Turck, D. Colle, M. Pickavet


Feel free to contact me through any of the below.