Coventry University Featured PhD Programmes
University of Leeds Featured PhD Programmes
Cardiff University Featured PhD Programmes

Deep Learning: Fully funded PhD studentship in Better Sample Efficiency of Reinforcement Learning with Neural Networks


School of Informatics

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
Prof Amos Storkey No more applications being accepted Funded PhD Project (Students Worldwide)

About the Project

Keywords: Machine Learning, Neural Networks, Deep Learning, Deep Reinforcement Learning

We are advertising a fully funded (for 4 years) enhanced PhD position to work with Professor Amos Storkey in the School of Informatics at the University of Edinburgh, and with Kamil Ciosek at Microsoft Research Cambridge. The scholarship is funded by UKRI and Microsoft Research, Cambridge. The current deadline is 28th August (though applying earlier than the deadline is advantageous), and the start date is 1 Jan 2021, but can be a little flexible. Informal enquiries can be made to [Email Address Removed].

Deep reinforcement learning has had huge empirical success and is a major enabling technology for many applications of AI. However, recent RL algorithms still require millions of samples to obtain good performance. Since obtaining environment interactions is often costly and since challenging environments are rarely static, this inhibits many practical applications. This project will investigate ways of reducing this cost, aiming to find more sample-efficient RL algorithms. We aim for the algorithms to be deployable in realistic settings, where agents use deep networks to represent knowledge about the environment. Improving sample efficiency of RL has immediate applications to Microsoft’s efforts in applying RL games. It is also likely to lead to improved performance of other systems making automated decisions.

CANDIDATE’S PROFILE

• Candidates for this post must have evidence of good capability in mathematics and in programming (but the previous degree could be from one of many disciplines), and must be able to show a solid understanding of the fundamentals of machine learning across the breadth of the field. Experience of programming in PyTorch is desirable, as is some training in reinforcement learning. We are looking for candidates with the potential and drive to excel and be a future research leader in this field.
• An excellent Bachelors degree (ideally 1st class or international equivalent) and ideally further experience or evidence of excellence in Machine Learning (e.g. a Masters degree).
• Proficiency in English (both oral and written).
• Students must be eligible for EPSRC funding, that is they should have sufficient connection to the UK, usually established via UK residency for 3 years or more and having no restrictions on how long they can stay in the UK. For more information, see residency requirements at the top of the page: https://epsrc.ukri.org/skills/students/guidance-on-epsrc-studentships/eligibility/. If you are uncertain of your eligibility, then please do enquire.

APPLICATION INFORMATION

Applicants should apply via the University’s admissions portal (EUCLID) and apply for the programme PhD Informatics: Adaptive and Neural Computation; 3 Year, full time with a start date of 01 Jan 2021 or other preferred start date. This can be reached via https://www.ed.ac.uk/studying/postgraduate/degrees?r=site/view&id=489

Applicants should state “Better Sample Efficiency of Reinforcement Learning” as the topic and designate “Amos Storkey (MSR Scholarship)” as the research supervisor in their application and Research Proposal document.

Applications should be submitted before the first deadline for consideration, which is 28th August 2020; applying earlier than the deadline is advantageous. If the position is not filled after that deadline applications will be considered until the position is filled. The suggested start date is 01 Jan 2021, but other start dates can be considered.

Applicants must submit:

• All degree transcripts and certificates (and certified translations if applicable)
• Evidence of English Language capability (where applicable).
• A short research proposal (max 2 pages)
• A full CV and cover letter describing your background, suitability for the PhD, and research interests (max 2 pages).
• Two references (note that it the applicant’s responsibility to ensure reference letters are received before the deadline).

Only complete applications (i.e. those that are not missing the above documentation) will progress forward to Academic Selectors for further consideration.

ENVIRONMENT

The School of Informatics at the University of Edinburgh is unique in its Machine Learning and AI research and provision in Europe. The school has over 100 academic staff and over 400 PhD students. Researching in AI continuously since 1963, it is now home to over 60 academic staff across the breadth of AI, 4 Centres for Doctoral Training in AI. It has a long-standing relationship with Microsoft Research, Cambridge. The student will join an immediate team of 15 researchers, and have a broader set of more than 50 researchers in related fields. The student will receive active hands-on supervision from both supervisors.

Funding Notes

This PhD Scholarship covers the fees and stipend, and additional conference travel and equipment. In addition, travel and subsistence for spending time at Microsoft Research, Cambridge will be available.

A studentship starting in the academic year 2020/21 covers:

• Full time PhD tuition fees for a student with sufficient connection to the UK. (£4,407 per annum, subject to annual increment).
• A tax free minimum stipend of GBP £15,285 per year for 4 years, plus an additional enhancement of £500 pa each year.
• Additional programme costs of £1000 per year.

Note eligibility requirements for EPSRC funding in candidate's profile.

References

https://homepages.inf.ed.ac.uk/amos/


FindAPhD. Copyright 2005-2020
All rights reserved.