Public defence in Computer Science, M.Sc. (Tech) Mustafa Mert Çelikok
Opponent: Associate Professor Matthew E. Taylor, University of Alberta, Canada
Custos: Professor Samuel Kaski, Aalto University School of Science, Department of Computer Science
The thesis is publicly displayed 10 days before the defence in the publication archive Aaltodoc of Aalto University.
Public defence announcement:
Interaction of humans and AI systems is becoming ubiquitous. Specifically, recent advances in machine learning have allowed AI agents to interactively learn from humans how to perform their tasks. The main focus of this line of research has been to develop AI systems that eventually learn to automate tasks for humans, where the end goal is to remove the human from the loop, even though humans are involved during training. However, this perspective limits the applications of AI systems to cases where full automation is the desired outcome.
In this thesis, we focus on settings where an AI agent and a human must collaborate to perform a task, and the end goal of the AI is not to replace human intelligence, but to augment it. We propose a mathematical framework for human-AI collaboration scenarios where the goal of an AI agent is to augment the human intelligence instead of replacing it. The unifying theme of the thesis is that to augment its human partner, an AI agent must be able to infer a model of its partner. In order to model human users, we bring in prior knowledge from cognitive science and behavioural economics, where various mathematical models of human decision-making have been developed. We demonstrate that, using the methods developed in this thesis, sufficient statistics of human behaviour can be drawn from these models, and incorporated into multi-agent reinforcement learning, in order to facilitate better human—AI collaboration.
Contact details of the doctoral student: [email protected]