Sotabase

Career

· Associate Professor, University of Amsterdam2024–
· Assistant Professor, University of Amsterdam2018–2024
· Postdoctoral Researcher, McGill University2016–2018
· PhD in Computer Science, TU Darmstadt2011–2016
· Master of Science in Artificial Intelligence, University of Groningen2008–2011
· Bachelor of Science in Artificial Intelligence, University of Groningen2005–2008

Publications (77)

Addressing Function Approximation Error in Actor-Critic Methods
International Conference on Machine Learning · 2018
6,328
cited
Attention, Learn to Solve Routing Problems!
International Conference on Learning Representations · 2018
1,498
cited
Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement
International Conference on Machine Learning · 2019
267
cited
BanditSum: Extractive Summarization as a Contextual Bandit
Conference on Empirical Methods in Natural Language Processing · 2018
187
cited
Buy 4 REINFORCE Samples, Get a Baseline for Free!
DeepRLStructPred@ICLR · 2019
187
cited
Learning robot in-hand manipulation with tactile features
IEEE-RAS International Conference on Humanoid Robots · 2015
177
cited
Stable reinforcement learning with autoencoders for tactile and visual data
IEEE/RJS International Conference on Intelligent RObots and Systems · 2016
177
cited
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
Neural Information Processing Systems · 2020
175
cited
Deep Policy Dynamic Programming for Vehicle Routing Problems
Integration of AI and OR Techniques in Constraint Programming · 2021
150
cited
Towards learning hierarchical skills for multi-phase manipulation tasks
IEEE International Conference on Robotics and Automation · 2015
135
cited
Probabilistic inference for determining options in reinforcement learning
Machine-mediated learning · 2016
119
cited
Stabilizing novel objects by learning to predict tactile slip
IEEE/RJS International Conference on Intelligent RObots and Systems · 2015
119
cited
Active tactile object exploration with Gaussian processes
IEEE/RJS International Conference on Intelligent RObots and Systems · 2016
108
cited
A Survey of Exploration Methods in Reinforcement Learning
arXiv.org · 2021
101
cited
Deep Generative Modeling of LiDAR Data
IEEE/RJS International Conference on Intelligent RObots and Systems · 2018
91
cited
Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems
ACM Conference on Recommender Systems · 2020
87
cited
Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments
IEEE Transactions on robotics · 2014
80
cited
Experimental design for MRI by greedy policy search
Neural Information Processing Systems · 2020
63
cited
Estimating Gradients for Discrete Random Variables by Sampling without Replacement
International Conference on Learning Representations · 2020
56
cited
Learning to predict phases of manipulation tasks as hidden states
IEEE International Conference on Robotics and Automation · 2014
52
cited
Sotabase
Herke van Hoof | Researcher Profile | Sotabase | Sotabase