Jul 2026
Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning
A principled reward decomposition framework is introduced that decouples verifiability from sparsity, and two new reward functions are proposed: an exponential reward that provides graded penalties based on the count of forbidden-concept occurrences, and a PageRank inspired reward that weights penalties by semantic importance.
Efstratios Zaradoukas, Davide Gabrielli, Bardh Prenkaj et al.
· arXiv.org · 1 citation