PostDoc Position on Reinforcement Learning from Human Feedback

TU Delft offers a 2-year PostDoc position on Reinforcement Learning from Human Feedback for mobility system design, focusing on AI-based recommender systems and addressing key algorithmic challenges.

TU Delft is offering a 2-year PostDoc position focused on Reinforcement Learning from Human Feedback (RLHF) for mobility system design. The research will build on RLHF techniques to develop AI-based recommender systems, addressing challenges such as multiple objectives and design transparency.

Key aspects of the position include:

• Developing RLHF techniques for mobility system design
• Addressing algorithmic challenges like multiple objectives and robustness
• Ensuring transparency in the design recommendation process

The PostDoc will be part of the Sequential Decision Making group within TU Delft’s Intelligent Systems department, collaborating with TNO and TU Delft’s Transport & Planning department. For more information, visit the vacancy details and the project website.

Tags: Reinforcement Learning, PostDoc position, TU Delft, Mobility System Design, AI-based recommender systems, Human Feedback