PhD Studentship: Causal Reinforcement Learning

Develop foundational research that makes reinforcement learning more robust and generalizable by integrating causal reasoning into sequential decision-making. You’ll work with an academic supervisor at the University of Cambridge and industrial co-supervisors at Phaidra, progressing from theory (offline RL, confounding/mediators) to algorithm development (causal structure, out-of-distribution generalization, policy guarantees) and benchmarking on controlled simulated environments.