Postdoc Bayesian Reinforcement Learning Learning to Collaborate Humans

Overview

Are you passionate about AI and do you want to advance the frontier of human-AI collaboration?

Job description

We are seeking a motivated postdoctoral researcher to join our team and explore the intersection of Bayesian reinforcement learning, deep learning and human-AI interaction. This position focuses on developing adaptive algorithms that enable AI agents to learn, reason, and collaborate effectively with human partners in dynamic, uncertain environments. By integrating Bayesian reasoning you will address the sample complexity of reinforcement learning, making it applicable to human-AI collaboration settings.

Why build AI systems that replace people if we can build AI systems that collaborate with people? Hybrid Intelligence (HI) is the combination of human and machine intelligence, expanding human intellect instead of replacing it. Our goal is to design Hybrid Intelligent systems, an approach to Artificial Intelligence that puts humans at the center, changing the course of the ongoing AI revolution.

At Delft University of Technology we are looking for a postdoc who wants to push machine learning beyond traditional settings that assume a fixed dataset. Specifically, collaborating with people requires both reasoning about the sequential aspects of the interaction, as well as adapting based on very few data points. Many reinforcement learning methods, however, require a very large set of experience.

We aim to lower this sample complexity by building exploring reasonable assumptions (e.g., from cognitive psychology) on goals and behaviors of humans, thus making an important step towards AI that can effectively adapt to its human collaborator.

The postdoc will be based in the sequential decision making group at the department of intelligent systems, and will benefit from the network provided by the ELLIS Unit Delft.

Additionally, this postdoc position is part of the Hybrid Intelligence project and the successful candidate will be supervised by Dr. Frans Oliehoek (TU Delft) and Dr. Jan Willem van de Meent (University of Amsterdam). The successful candidate will attend project meetings and actively collaborate with a variety of project partners.

• Conducting independent research in reinforcement learning, with a focus on human-AI interaction.
• Disseminating research outcomes through publications, conferences, and workshops.
• Actively contributing to the larger research project goals of Hybrid Intelligence.
• Contributing to education, e.g. by supervising bachelor or master theses.

Strict requirements:

• A PhD degree in AI or closely related topics in computer science, math, or physics.

Other desiderata:

• Thorough knowledge of general area of reinforcement learning, decision making under uncertainty, and/or other forms of interactive machine learning.
• Track record with international publications.
• Good coding skills and experience in contemporary machine learning frameworks (e.g., PyTorch).
• Fluent in English
• Self-motivated
• Team player: willing to initiate collaborations with other partners in the project.

TU Delft (Delft University of Technology)

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

At TU Delft we embrace diversity as one of our core values and we actively engage to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale.

That is why we invite you to apply. Your application will receive fair consideration.

Challenge. Change. Impact!

Faculty of…