Matt MacDermott
PhD Student at Imperial College London, Centre for Doctoral Training in Safe and Trusted AI. Member of the Causal Incentives Working Group. mjm121 at ic.ac.uk
News
- January 2024: I took part in the Alignment Research Engineer Accelerator Programme.
- October 2023: I helped organised the Agent Foundations for AI Alignment Workshop.
Publications
- Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt (2024). The Reasons that Agents Act: Intention and Instrumental Goals. International Conference on Autonomous Agents and Multiagent Systems.
- Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt (2023). Discovering Agents. Artificial Intelligence.
- James Fox, Matt MacDermott, Lewis Hammond, Paul Harrenstein, Alessandro Abate, Michael Wooldridge (2023). On Imperfect Recall in Multi-Agent Influence Diagrams. Theoretical Aspects of Rationality and Knowledge. (TARK 2023 Best Paper Award)
- Matt MacDermott, Tom Everitt, Francesco Belardinelli (2023). Characterising Decision Theories with Mechanised Causal Graphs. Games, Agents and Incentives Workshop; International Conference on Autonomous Agents and Multiagent Systems.