2026
Universal Value-Function Uncertainties
Moritz Akiya Zanger, Max Weltevrede, Yaniv Oren, Pascal R. Van der Vaart, Caroline Horsch, Wendelin Boehmer +1
ICLR 2026poster
Estimating epistemic uncertainty in value functions is a crucial challenge for many aspects of reinforcement learning (RL), including efficient exploration, safe decision-making, and offline RL. While deep ensembles provide a robust method for quantifying value uncertainty, they come with significan…