PhD Studentship: Reinforcement Learning and Generative AI for Future Wireless Networks

The project:

An exciting opportunity is available for a talented and motivated PhD candidate to pursue cutting-edge research on applying generative artificial intelligence and reinforcement learning techniques to enable intelligent control in Open Radio Access Network (O-RAN) systems.

Based at the University of Bristol and fully funded by EPSRC and BT for 4 years, this PhD project sits at the intersection of wireless communications, machine learning, and next generation mobile network architectures. The focus will be on developing novel AI methodologies to add decision-making and automation capabilities across the O-RAN intelligent controller framework.

The project will explore Off-line reinforcement learning, also known as batch reinforcement learning, In Off-line RL the agent learns from a fixed dataset of experiences, rather than interacting directly with the environment in real-time. Off-line reinforcement learning can be beneficial in scenarios where online exploration is costly, dangerous, or impractical, such as in robotics, healthcare, or communications network management. By leveraging pre-existing data, off-line reinforcement learning algorithms can learn effective policies without the need for extensive online exploration, potentially reducing the risk of failures or disruptions.

As the ideal candidate you will have exceptional creativity and strong fundamentals in areas such as deep learning, neural networks, generative modelling, multi-agent reinforcement learning, wireless networking or network management. Experience with O-RAN or related technologies is not essential as long as you have the drive and aptitude to rapidly get up to speed. 

In addition to the compelling research, this studentship provides generous support including conference/travel funds to present at top AI and wireless networking venues. You will also receive excellent researcher training, have opportunities to collaborate with AI researchers at BT, and be embedded within our world-leading environment here at Bristol. 

How to apply:

Prior to submitting an online application, you will need to contact the project supervisor to discuss.

Online applications are made at http://www.bris.ac.uk/pg-howtoapply. Please select Electrical and Electronic Engineering PhD on the Programme Choice page. You will be prompted to enter details of the studentship in the Funding and Research Details sections of the form (Reference number 240045).

Candidate requirements: 

Applicants must hold/achieve a minimum of a merit at master’s degree level (or international equivalent) in a science, mathematics or engineering discipline. Applicants without a master's qualification may be considered on an exceptional basis, provided they hold a first-class undergraduate degree. Please note, acceptance will also depend on evidence of readiness to pursue a research degree.

If English is not your first language, you need to meet this profile level: Profile E
Further information about English language requirements and profile levels.

Funding:

Minimum tax-free stipend at the current UKRI rate (£19,237 for 2024/25), plus a £2,500 top up stipend amount each year.

In addition to the compelling research, this studentship provides generous support including £10K towards conference/travel funds to present at top AI and wireless networking venues worldwide.

Contacts:

For questions about the research topic, please contact

Professor Robert Piechocki r.j.piechocki@brisrol

or  

Dr Shuping Dang shuping.dang@bristol.ac.uk

or

Dr James Pope jp16127@bristol.ac.uk

Advert information