We are looking for applicants for a fully funded PhD (£20,700 per annum
bursary plus the payment of the student fees) in the areas of Continual and
Open-ended Reinforcement Learning at the Computer Science Department of the
University of Hertfordshire, United Kingdom (deadline 14/11/2025).
**PhD Project**
Recent advancements in Artificial Intelligence (AI) have resolved
challenges once deemed insurmountable just a decade ago, and RL is at the
core of this breakthrough. However, most RL methods still struggle to
operate effectively in truly open-ended, non-stationary environments. This
project will push the boundaries of RL by investigating how agents can
continuously learn and adapt over time; how they can autonomously develop
and flexibly apply an ever-expanding repertoire of skills across various
tasks; and what representations allow them to do this efficiently.
Addressing these questions is crucial for creating AI systems that, despite
limited computational resources, can sustain autonomous learning and
adaptation in ever-changing environments throughout their lifetime—becoming
increasingly knowledgeable and capable. The selected candidate will have
the opportunity to master and contribute to cutting- edge techniques in
deep reinforcement learning, incorporating principles from probabilistic
machine learning, information theory, intrinsic motivation, continual and
open-ended learning frameworks. The project will employ computer games as
benchmarking tools and/or apply its findings to robotic systems (in
simulations or on real-world platforms), including manipulators,
intelligent autonomous vehicles, and humanoid robots.This PhD project
offers a unique chance to explore some of the most profound and fascinating
questions in artificial intelligence today, providing the opportunity to
make a significant contribution to a field at the forefront of AI research.
**Requirements**
We are looking for a student who is motivated and passionate about
Artificial Intelligence. A background in computer science or mathematics,
together with strong programming skills, are essential requirements.
Experience in reinforcement learning or robotics are desirable and will be
considered a plus during the selection process. The applicant will be
expected to disseminate her/his work publishing scientific articles and/or
participating at international conferences. To be fluent in English is
mandatory.
**Where**
The PhD will take place in the Adaptive System research group of the
Computer Science department of the University of Hertfordshire, United
Kingdom. The group is specialised in probabilistic/information-theoretic
approaches to Artificial Intelligence, used for a wide range of
applications such as robotics, video-games and cognitive modelling.
According to the Research Excellence Framework 2021, the University of
Hertfordshire is ranked in the top 25% of all UK universities for research
impact and research in Computer Science has been recognised as excellent,
with 90% of the research submitted and all of the research impact rated as
internationally excellent or world leading. The University of Hertfordshire
has ranked second in the UK 2023 Postgraduate Taught Experience survey,
providing a very stimulating environment, offering a large number of
specialised and interdisciplinary seminars as well as general training and
researcher development opportunities. The University is situated in
Hatfield, in the green belt just 25 minutes by train to London.
**How to Apply**
The application must be done following the procedure indicated in this
website:
Interested applicants may want to contact Dr. Nicola Catenacci Volpi (
n.catenacci-volpi@herts.ac.uk) to discuss the project, the PhD program at
the University of Hertfordshire and details about the application process.
**Deadline**
14/11/2025
*-----------------------------------*
Dr. Nicola Catenacci Volpi, PhD
Research Fellow in Information Theory for AI & Robotics
Adaptive Systems Research Group
The University of Hertfordshire
Department of Computer Science
College Lane
Hatfield, Hertfordshire AL10 9AB
United Kingdom
E-mail: n.catenacci-volpi@herts.ac.uk
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************
Posts
