When Do Intrinsic Rewards Lead to Exploration?

Excerpt

arXiv:2610.02159v1 Announce Type: new Abstract: Intrinsic rewards are designed to guide exploration in reinforcement learning by assigning value to an agent's experience, for example through prediction error or learning progress. However, maximizing these rewards need not produce the most informative experience available. We propose a formal criterion for exploration that compares policies by the counterfactual information they acquire: how well their histories can substitute for experience unde