Fully Funded PhD in Restless-Bandit-Enhanced Multi-Agent Reinforcement Learning

About the role

We are seeking a highly motivated candidate to join a fully‑funded PhD project at RMIT University. The research focuses on Restless‑Bandit‑Enhanced Multi‑Agent Reinforcement Learning, aiming to develop scalable algorithms for high‑dimensional decision problems.

Key responsibilities

• Design and implement novel restless‑bandit and reinforcement‑learning algorithms.
• Conduct extensive simulations to evaluate learning‑control trade‑offs.
• Analyse theoretical performance guarantees and publish findings in peer‑reviewed venues.
• Collaborate with supervisors and contribute to research meetings.

Required profile

• Basic knowledge of probability theory, reinforcement learning or optimisation.
• Strong programming ability for simulation work.
• Motivation to pursue a research doctorate.

Required skills

• Python programming.
• Understanding of reinforcement‑learning concepts.
• Familiarity with probability and optimisation techniques.
• Experience with simulation development.

What we offer

• Fully funded Australian Research Council Discovery Grant scholarship covering tuition and living stipend.
• Opportunity to work with internationally recognised researchers.
• Access to RMIT’s research facilities and collaborative environment.