EPSRC/BAE Systems INDUSTRIAL CASE PhD Studentship - "Mitigation of Reinforcement Learning Algorithms in Changing Environments"

Under this research studentship, the successful candidate will conduct research as part of the EPSRC Industrial CASE Award funded project.

Theme of the PhD project:

The development of (deep) Reinforcement Learning (RL) algorithms to train agents within game environments is well known. Agent training is typically conducted against a known, simplified, or constrained environment. However, the deployed environment is typically more complex, and subject to some change and uncertainly not represented in the training environment. RL algorithms typically characterise performance against probabilistic arenas, rather than being able to cope with an environment that is subject to change over time. The performance of the resulting RL agent can then be expected to become compromised over time, but not necessarily be catastrophic. In this PhD project, we are concerned with (i) understanding this performance degradation and (ii) the development of mitigating strategies. More specifically, the project will focus at creating a train-and-test framework comprising a simulation engine for dynamic environment and a configurable RL approach. In addition to considering changes in the environment, the simulator and RL agent will need to account for real-world challenges, such as multiple conflicting objectives, robustness, and safety issues.

The team at BAE Systems is focused on cutting-edge research in advanced simulation, optimization, and machine learning, and are thus invested in how RL can be extended to support decision making in dynamic environments. The project will therefore contribute directly to BAE Systems’ ongoing research. From a scientific perspective, this project will lead to cross-disciplinary research and output that is of high quality and significance.

Due to the nature of this topic, candidates may be subject to a security check.

Supervision:

The successful candidate will be supervised by Professor Richard Allmendinger, Dr. Theodore Papamarkou and Dr. Wei Pan from The University of Manchester.

Nature of the studentship:

The 4-year studentship, commencing in September 2023, will cover full tuition fees and a stipend equivalent to UKRI rates (£16,062 tax free in 2022/23), plus an industrial top-up stipend from BAE Systems, subject to contract. It also provides travel support for fieldwork, conferences and annual visits to BAE Systems. This project is available for UK students but we are able to offer a limited number of scholarships that will enable full studentships to be awarded to European applicants.

Entry Requirements:

Applications are sought from talented and motivated UK and European candidates with an academic background in at least one of these fields: (Deep/multi-agent) reinforcement learning, deep learning, Gaussian processes, Bayesian optimization, transfer/online/meta-learning/safe/multitask learning, dynamic control.

Applicants must hold:

• 1^st or 2:1 Honours degree (or equivalent), and
• Masters degree with Distinction

English Language requirements (where required) are IELTS 7.0, TOEFL 623 (100 ibt), PTE 76.

Application: Candidates should submit a PhD application (including all supporting documents) for the PhD Business & Management, and indicate that they wish to be considered for the EPSRC/BAE Systems INDUSTRIAL CASE PhD Studentship.

The application must contain:

• Research proposal (500-1000 words) related to the topic, and
• Written statement clearly indicating how your research competencies and interests to date are aligned with the specific nature of the PhD projects.

Application Deadline: 28^th February 2023

Enquiries

Further details about the project, contact richard.allmendinger@manchester.ac.uk) with an up-to-date CV including any publication profile.

Making your application: ambs-pgresearch@manchester.ac.uk

Advert information