Biography
Peter Tisnikar is a postdoctoral researcher in the Machine Learning Research Group at the University of Oxford, working with Professors Stephen Roberts and Michael Osborne. His current research focuses on Inverse Reinforcement Learning for aligning AI systems with human preferences and values. Peter completed his PhD at King’s College London and Imperial College London, where he developed methods enabling robots and autonomous agents to effectively collaborate with people of diverse capabilities. His work also explored the use of physiological signals, such as eye gaze, to infer human affective states during interaction, with the goal of enhancing the quality and comfort of human—robot interactions. His main research interest is development of intelligent agents that continuously adapt and tailor their behaviour to diverse users, enabling productive and personalised collaboration, assistance, and alignment.
Research Interests
- Preference Learning
- Inverse Reinforcement Learning
- Human Modelling
- Human--Agent Teaming
