PhD Position Tropical Kernel-Based Offline Reinforcement Learning

This PhD position focuses on developing a novel approach to offline reinforcement learning using tropical kernel-based function approximation. The candidate will establish the theoretical foundation and design scalable algorithms for this approach, and also engage in teaching activities as part of their PhD trajectory.

Requirements

• Relevant MSc degree in systems and control, computer science, engineering, applied mathematics, or a related field.
• Solid mathematical background, including comfort with linear algebra, analysis, probability, optimization, and ideally some functional analysis or approximation theory.
• Experience with (convex) optimization and algorithm design.
• Experience with kernel methods is a plus but not required.
• Excellent command of the English language and communication skills.

Benefits

• 4-year period of employment in principle, but in the form of 2 employment contracts.
• Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from €3059 - €3881 gross per month, from the first year to the fourth year based on a fulltime contract (38 hours), plus 8% holiday allowance and an end-of-year bonus of 8.3%
• Enrollment in the TU Delft Graduate School with access to an inspiring research environment and academic staff.
• Customisable compensation package, discounts on health insurance, and a monthly work costs contribution.
• Flexible work schedules can be arranged.