Game AI PhD in Computer Science
Multi-Agent Reinforcement Learning for Game AI and Robotic Control - EPSRC NPIF PhD studentship in partnership with Accelerated Dynamics
- Host instituition: University of York
- Qualification type: PhD
- Location: York
- Funding for: UK citizens and EU citizens who have resided in the UK for the past three years (EPSRC eligibility requirements apply)
- Duration: Funding is available for a minimum of 3 years and up to a maximum of 4 years
- Funding amount: Full coverage of tuition fees and annual stipend at RCUK rate i.e. £14,553 for 2017/18
- Hours: Full Time
- Placed on: 30 June 2017
- Closes: 31 August 2017 (Applications may close earlier than the advertised deadline if a suitable candidate is found).
The Internet of Things and connected devices are creating opportunities for increased automation. We are progressing to a point where everything is connected (from the smallest sensor to self-driving cars and aerial drones) but the way we interact with each of these is currently limited to one-one interactions.
This project will research and develop multi-agent reinforcement learning algorithms for controlling swarms of agents, enabling an individual to control vast numbers of connected devices simultaneously.
These algorithms will initially be tested in Starcraft to enable rapid iteration. Later in the PhD, using Accelerated Dynamics robotic platform, these algorithms will be tested in real world scenarios with swarms of aerial drones.
If successful, you will conduct your research under the supervision of:
- Dr Sam Devlin, Research Fellow / Lecturer in Artificial Intelligence and Games.
- Professor Peter Cowling, Director of Digital Creativity Labs and the Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI)
- Accelerated Dynamics (based in London).
You will be part of a large and internationally leading team who specialise in games and artificial intelligence. The team has a substantial track record in industrial-academic research, and have been very successful at delivering research results into commercial games. The team includes 23 permanent members of academic staff and 10 post-doctoral research associates within the Digital Creativity Labs, and currently 34 PhD students in the closely linked centre for doctoral training. The team is highly supportive and encourages cross-project collaboration, especially on joint publications and developing new research projects. You will collaborate closely with roboticists at Accelerated Dynamics, and there may be opportunities to spend time at their offices to maximise the two-way knowledge transfer between the student and the staff at Accelerated Dynamics.
If successful, you will be supported for a maximum of four years. Funding includes:
- £14,553 (2017/18 rate) per year stipend
- Home/EU tuition fees
- RTSG (training/consumables/travel) provision
To be considered for this funding you must:
- meet the entrance requirements for a PhD in Computer Science
- be eligible to pay home/EU fees and be able to meet the EPSRC requirements: here *
* EU applicants who do not meet the EPSRC residency requirements can apply to be considered for a fees only award
We will look favourably on applicants that can demonstrate knowledge of machine learning (especially reinforcement learning) and who have excellent Python programming skills.
Apply for this studentship
1. Apply to study
You must apply online for a full-time PhD in Computer Science here
You must quote the project title (EPSRC NPIF Studentship Accelerated Dynamics) in your application.
There is no need to write a full formal research proposal in your application to study as this studentship is for a specific project.
2. Provide a personal statement
As part of your application please provide a personal statement of 500-1,000 words with your initial thoughts on the research topic.
The closing date for the receipt of applications is Thursday, 31st August 2017 (Applications may close earlier than the advertised deadline if a suitable candidate is found).
Interviews are expected to take place within approx. 14 days of the closing date.
The studentship must begin in October 2017.
Dr Sam Devlin email@example.com
firstname.lastname@example.org +44 (0)1904 325404