PhD Studentship: Causal Reinforcement Learning
Core
PhD research integrating causal inference with reinforcement learning to improve robustness and generalization of AI control systems in industrial settings.
Role type
PhD Researcher (Causal Reinforcement Learning)
Builds
RL algorithms leveraging causal structure for out-of-distribution generalization
Domain
Industrial automation, Causal Inference, Reinforcement Learning
Deliverable
production ML models
Required skills
reinforcement learning, probabilistic modelling, control theory, Python, PyTorch, NumPy, SciPy, scikit-learn
Preferred skills
causal inference, causal graphical models, offline RL, batch RL, safe RL, applying ML to physical systems
Technologies
PyTorch, NumPy, SciPy, scikit-learn
Responsibilities
formalising policy learning from biased datasets through a causal lens, building RL algorithms leveraging causal structure, evaluating methods on controlled simulated environments
Seniority
PhD Candidate, Research & Development
