Reinforcement Learning from Human Feedback Fund at University of Sheffield 2025

PhD Research Project: Reinforcement Learning from Human Feedback

• The Reinforcement Learning from Human Feedback PhD project, supervised by Dr. Bei Peng and Dr. Robert Loftin, focuses on developing new algorithms for reinforcement learning (RL) that can solve complex tasks without a predefined reward function.
• The project aims to enhance the effectiveness of RL systems by minimizing the need for human interaction while improving the learning from human feedback.

Eligibility

• To apply for the Reinforcement Learning from Human Feedback PhD project, applicants must have a 2.1 honours undergraduate degree (or equivalent) in Computer Science or a related field such as Physics, Mathematics, or Engineering.
• A Master's degree or equivalent is preferred. Non-native English speakers must have an IELTS score of 6.5, with no less than 6.0 in each component.

Application Process

• Applicants should submit their applications through the University of Sheffield Postgraduate Online Application Form.
• Ensure that Dr. Bei Peng and Dr. Robert Loftin are listed as the proposed supervisors.
• A research proposal (up to 4 A4 pages) outlining your reasons for applying, research approach, and relevant skills and experience in reinforcement learning should be included.
• The application deadline is April 18, 2025.

Benefits/Value

• The Reinforcement Learning from Human Feedback PhD project offers full funding for 3.5 years, covering standard UK home tuition fees and providing a tax-free stipend of £19,237 (for 2024/25).
• Overseas applicants are welcome to apply but must secure additional funding to cover the tuition fee difference.
• The project provides an excellent opportunity to work at the cutting edge of AI research within a world-leading department.