PhD and Postdoc Positions in Machine Learning / Reinforcement Learning / Evolutionary Computation at IT University of Copenhagen

Funded Postdoc and PhD positions are available to start as soon as possible or after agreement.

‍The positions are funded by two Independent Research Fund Denmark (DFF) grants led by Sebastian Risi (INNATE: DFF Sapere Aude grant and QD2L: DFF thematic grant). Please refer to which project you are applying to.

Project 1 (INNATE):
The overall aim of this project is to create adaptive machines that can continually learn from experience and apply previously learned knowledge to novel situations. Current machine learning systems can only deal with situations they have been trained for in advance; they are unable to adapt quickly and during execution to unexpected events. In the INNATE project, the goal is to devise a new class of algorithms based on a combination of evolutionary computation and state-of-the-art reinforcement learning to significantly extend the usefulness of simulated agents and robots.

‍Project 2 (QD2L):
Deep neural networks have lately shown impressive performance across a range of tasks, such as face recognition, speech recognition, or automatic translation. However, there is increasing evidence that while these systems work well on the data they are training on, they do not generalize well to related problems or even different instances of the same problem. The aim in this project is to devise a novel approach to making neural networks significantly more robust by combining deep (reinforcement) learning methods with ideas from quality diversity search methods.

Further details:
PhD and Postdoc Positions in Machine Learning / Reinforcement Learning / Evolutionary Computation at IT University of Copenhagen