cs.LGJun 2, 2026

Exact Unlearning in Reinforcement Learning

Authors: Thanh Nguyen-TangRaman Arora

Abstract

We formulate the problem of \emph{exact unlearning} in reinforcement learning, where the goal is to design an efficient framework that enables the removal of any user's data upon deletion request, i.e., the online learner's output after unlearning is \emph{indistinguishable} from what would have been produced had the deleted user never interacted with the learner. For any ρ>0ρ>0, we show that there exists a reinforcement learning (RL) algorithm that is ρρ-TV-stable and supports an exact unlearning procedure whose expected computational cost is only a ρlnTρ\sqrt{\ln T} fraction of the computational cost of retraining from scratch. We construct such a ρρ-TV-stable RL algorithm for tabular Markov decision processes (MDPs), which achieves a regret bound of O(H2SAT+H3S2A+H2.5S2A/ρ)\mathcal{O}(H^2 \sqrt{SAT} + H^3 S^2 A + {H^{2.5} S^2 A}/ρ), where S,A,HS, A, H, and TT denote the number of states, the number of actions, the episode horizon, and the number of episodes, respectively. We also establish a lower bound of Ω(H ⁣SAT ⁣+ ⁣SAH/ρ)Ω(H\sqrt{\!SAT}\! +\! {SAH}/ρ) for ρρ-TV-stable RL algorithms, showing that our algorithm is nearly minimax optimal.

Explore similar work

CardsList