PhD Studentship: Causal Reinforcement Learning

📋 Description

• Theoretical RL with causal reasoning for robust policies.
• Develop algorithms leveraging causal structure to improve generalization.
• Benchmark methods in controlled simulations and real-world settings.
• Collaborate with Cambridge and Phaidra supervisors on challenging problems.
• Apply RL to industrial data-centre and infrastructure challenges.

🎯 Requirements

• Degree in CS, Mathematics, Engineering or Statistics.
• Strong background in RL, ML, probabilistic modelling, or control.
• Python proficiency: PyTorch, NumPy, SciPy, scikit-learn.
• Clear scientific writing; ability to communicate research.
• Eligibility to study at Cambridge; international welcome.
• Familiarity with causal inference or offline RL preferred.

🎁 Benefits

• Fully funded 4-year PhD studentship.
• Based at Cambridge with remote collaboration.
• Supervision from Cambridge and Phaidra.
• Foundational training and development opportunities.
• Asynchronous remote work culture and documentation-first.
• Opportunity to publish research results.