The University of Southampton
Email:
ik3n19@soton.ac.uk

Ilias Kazantzidis 

https://www.linkedin.com/in/ilkaza/

I am a PhD student at the UKRI Centre for Doctoral Training in Machine Intelligence for Nano-Electronic Devices and Systems (MINDS) of the University of Southampton, currently in the second year of the programme. The first year consisted of a number of taught modules related to Artificial Intelligence. I hold a Diploma (5-years undergraduate degree) in Electrical and Computer engineering from the Democritus University of Thrace (Greece) and an MSc in Artificial Intelligence from the University of Southampton.

My research is on Safe Reinforcement Learning and combines tools from Control Theory and Software Engineering. A big part of it focuses on the field of Human-Agent Interaction. In many real-world applications, where safety is of primary importance, plain reinforcement learning methods (even combined with deep learning) will fail. My goal is to build provably safe reinforcement learning agents for safety-critical real-world systems. Applications that can benefit from my research are mainly autonomous vehicles and a range of robotic tasks.

Research

Research interests

Machine Learning, Deep Learning, Reinforcement Learning, Online Learning, Human-Agent Interaction, Game Theory, Control Theory, Robotics, Software Engineering

Publications

Kazantzidis, Ilias, Norman, Timothy, Du, Yali and Freeman, Christopher (2022) How to train your agent: active learning from human preferences and justifications in safety-critical environments. International Conference on Autonomous Agents and Milti-Agent Systems 2022, Auckland, Auckland, New Zealand. 09 - 13 May 2022. (In Press)

Contact

Share this profile FacebookTwitterWeibo