Join us at Utrecht University and contribute to the development of Explainable Reinforcement Learning models for the energy-mobility-housing nexus!

Job description

Current advancements in energy technology has led to an increase in the use of photovoltaic panels in residential areas, and an increasing use of electric cars. Communities can now benefit from the energy produced by their own photovoltaic panels for daily energy use, as well as for charging their electric vehicles. However, it remains a challenge to manage the energy such that individuals maximize their use of energy in a just and fair manner.

In this research project, you will be working towards developing Reinforcement Learning (RL) models that intelligently manage the charging/discharging of electric vehicles in the energy-mobility-housing nexus. RL models, however, are often seen as “black-boxes”. To enhance transparency, you will design methods to reveal the decision-making structure of the models using Explainable Reinforcement Learning (XRL). This will allow for an in-detail analysis of the level of justness and fairness achieved with the proposed RL. For example, with XRL, you will quantify the distribution of benefits and costs that the RL decision strategy proposes across individuals. You will also identify driving factors and conditions that contribute to the decisions proposed by the RL model.

This Postdoc position is part of a Dutch NWO research project. Within the project, you will have the opportunity to collaborate with several Dutch universities and researchers from multi-disciplinary backgrounds, and several industrial partners.

Qualifications
We are looking for an enthusiastic new colleague who meets the following criteria:

• You hold a PhD degree in Computer Science, Applied Mathematics or Operations Research, or you are within a few months from defending your PhD;
• you are familiar with Reinforcement Learning, Explainable Reinforcement Learning (XRL), fairness in Reinforcement Learning models.
• familiarity with the topics of charging schemes for electric vehicles, electric grids, and a just energy transition is a plus;
• you have demonstrated programming skills (familiarity with Python is a plus);
• you are willing to work in a multi-disciplinary team with researchers, and with diverse teams of stakeholders;
• you possess collaboration and communication skills with an independent outlook in defining and solving research problems;
• you are proficient in English.

Offer
• A Postdoc position for 2 years;
• A full-time gross salary ranging from ;
• 8% holiday bonus and 8.3% end-of-year bonus;
• A pension scheme, partially paid parental leave, and flexible employment conditions based on the Collective Labour Agreement Dutch Universities

More information here:

https://www.uu.nl/en/organisation/working-at-utrecht-university/jobs/postdoc-position-in-explainable-reinforcement-learning