News

The Delta lab will host a talk by dr. Jens Kober on “Robots Learning (Through) Interactions” on May 7th. Due to current Covid-19 restrictions, the talk will be live-streamed. More information on the Delta lab page.

(Position is now closed)

We have an open PhD position on the topic of using symbolic knowledge representation as prior knowledge in reinforcement learning systems. This position is part of the Hybrid Intelligence centre, where we are currently recruiting 13 PhDs and postdocs across the Netherlands with another 14 positions to be announced soon. To directly apply for the position on hybrid approaches for learning sequential behavior, click here.

 

Wouter Kool’s paper on ancestral Gumbel-top-K sampling for sampling without replacement from large structured domains is now published in JMLR (Kool, van Hoof & Welling, pdf). Congratulations, Wouter!

Jan Wöhlke and Elise van der Pol got their submissions accepted to AAMAS! Congrats Jan & Elise! Publication details will appear shortly on the Delta lab website.

We are looking for a PhD student / Postdoc to join AMLAB to work on the topic of reinforcement learning with partial or inaccurate models. More information regarding the position and application procedure on our institute’s website. On the topic of hiring, our institute is currently also seeking a associate or full professor in Machine Learning.

Wouter Kool’s paper on estimating gradients for structured discrete domains has been accepted to ICLR (Kool, van Hoof & Welling, pdf ). Congratulations, Wouter!

Two ICML papers were accepted: An Inference-Based Policy Gradient Method for Learning Options (Smith, Van Hoof & Pineau; pdf) and Addressing function approximation error in actor-critic methods (Fujimoto, Van Hoof & Meger; pdf). Congrats Matt & Scott!

I started a new job at the university of Amsterdam (UVA) as Universitair Docent (Assistant professor). I am in the process of relocating and updating my website, so for the time being not all information on the website is accurate.

New paper accepted at ICRA: V. Barbaros, H. van Hoof, A. Abdolmaleki & D. Meger: A Comparison of Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control. Draft coming soon. Congrats, Victor!

Our paper “Learning of Non-Parametric Control Policies with High-dimensional State Features” was accepted for publication in JMLR. A draft is available on the publications page.