3 papers
cs.LG2025
VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills
Erik M. Lintunen
In self-supervised reinforcement learning (RL), one of the key challenges is learning a diverse set of skills to prepare agents for unknown future tasks. Despite impressive advance…
cs.AI2025
Towards a Formal Theory of the Need for Competence via Computational Intrinsic Motivation
Erik M. Lintunen, Nadia M. Ady, Sebastian Deterding +1
Computational modelling offers a powerful tool for formalising psychological theories, making them more transparent, testable, and applicable in digital contexts. Yet, the question…
cs.AI2024
Diversity Progress for Goal Selection in Discriminability-Motivated RL
Erik M. Lintunen, Nadia M. Ady, Christian Guckelsberger
Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a…