One of the most fundamental problems in artificial intelligence (AI) is how to enable autonomous development of action hierarchies, in other words, how to endow artificial agents with the ability to autonomously form useful high-level behaviours (for example, grasping) from existing behavioural units (for example, primitive sensory and motor actions available to a robot). This ability allows a developmental process during which an agent can learn to display behaviours of increasing complexity through continuously building on its existing set of skills to acquire new ones. For example, grasping may be followed by manipulating objects in different ways, which may be followed by using a key to unlock the door to an adjacent room, and so on, forming a continuously growing hierarchy of behaviours.
This project will develop algorithms that enable artificial agents to go through such developmental processes autonomously. As a result, artificial agents will develop the capability of performing tasks of increasing difficulty without guidance tailored for the specific domains in which they operate. This type of open-ended developmental process is fundamentally different from how artificial agents learn to perform complex tasks today and has the potential to dramatically increase their capabilities.
The project will use the elegant theoretical framework of reinforcement learning. The algorithmic approaches explored will depend on the background and interests of the student. Application areas may include, but are not limited to, engineering and robotics.
The project will be supervised by Dr Özgür Şimşek at the Department of Computer Science at the University of Bath. The University is located in the UNESCO World Heritage city of Bath, providing a vibrant research environment in one of the most beautiful areas in the UK.
Informal enquires are welcome and should be directed to Dr Özgür Şimşek (firstname.lastname@example.org).
This project is associated with the UKRI Centre for Doctoral Training (CDT) in Accountable, Responsible and Transparent AI (ART-AI). We value people from different life experiences with a passion for research. The CDT's mission is to graduate diverse specialists with perspectives who can go out in the world and make a difference.
Applicants should hold, or expect to receive, a First or Upper Second Class Honours degree in a relevant subject. A master’s level qualification would also be advantageous. Desirable qualities in candidates include intellectual curiosity, a strong background in mathematics and programming experience.
Formal applications should be accompanied by a research proposal and made via the University of Bath’s online application form. Enquiries about the application process should be sent to email@example.com.
Start date: 2 October 2023.