Erik Matias Lintunen
I'm a PhD student at the University of Alberta, working with Marlos C. Machado on representation-driven discovery of temporal abstractions for reinforcement learning. I'm part of the ReAL and RLAI labs, Amii, and the IMOL community. Previously, I spent several years at Aalto University studying intrinsically motivated skill learning and how individual differences in cognition predict everyday digital skills.
How do humans and machines turn experience into knowledge and skills? I'm interested in how deep reinforcement learning systems form representations through interaction with a big and noisy world, and how those representations can support lifelong learning. Longer term, I hope to use computational models to better understand how humans learn and make decisions.
Getting here has been wonderfully non-linear: I have formal training in sound art, information experience design, mathematics, statistics, and computational methods. Along the way, I've worked as a sound engineer in the performing arts, a technical producer on large-scale radio broadcasting projects, a software engineer, and a lecturer in digital arts and computing.
News
- Sep 2026Started my PhD at the University of Alberta with Marlos, supported by an NSERC Canada Impact+ Research Training Award (CIRTA) and a U of A President's Doctoral Prize of Distinction.
- Mar 2026Gave an invited talk on skill diversity in goal-conditioned RL at the Flowers AI & CogSci lab, Inria.
- Dec 2025“VendiRL: A framework for self-supervised reinforcement learning of diversely diverse skills” presented at the NeurIPS SEA workshop.
- Sep 2025Started a research visit with Marlos at the University of Alberta and Amii, supported by a Researchers Abroad grant, co-funded by the KAUTE Foundation, the Walter Ahlström Foundation, the Foundation for Economic Education, and the Nokia Foundation.
- Sep 2025“Advancing self-determination theory via computational modelling: The case of competence and optimal challenge” published in Motivation and Emotion.
- Sep 2025Co-organised the IMOL workshop at the University of Hertfordshire.
- Jul 2025“Towards a formal theory of the need for competence via computational intrinsic motivation” accepted at CogSci.
- Jun 2025Presented two posters at the RLDM conference in Dublin.
- Dec 2024“Diversity progress for goal selection in discriminability-motivated RL” presented at the NeurIPS IMOL workshop.
- Dec 2024“Cognitive abilities predict performance in everyday computer tasks” published in the International Journal of Human-Computer Studies. Awarded Nordic Mensa Fund’s Article of the Year prize.