Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Safe-RULE: Safe Reinforcement UnLEarning

About

Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems. However, its reliance on static datasets exposes offline Safe RL to data poisoning attacks, where adversaries inject malicious samples that compromise safety and induce unsafe policy behavior. In this work, we propose a new learning paradigm, named safe reinforcement unlearning (Safe-RULE), used as a defense framework to remove the influence of poisoned data without retraining from scratch or requiring access to the original training environment. We further extend reinforcement unlearning to offline Safe RL by explicitly accounting for both task performance and safety constraints during the unlearning process. Experiments across benchmark Safe RL tasks demonstrate that our approach effectively enhances safety performance against data poisoning attacks.

Shixiong Jiang, Taozheng Zhu, Fanxin Kong• 2026

Related benchmarks

TaskDatasetResultRank
Safe Reinforcement LearningSafety-Gymnasium PointGoal OSRL
Cost2.3
48
Safe Reinforcement LearningSafety-Gymnasium CarCircle OSRL
Cost0.00e+0
48
Safe Reinforcement LearningSafety-Gymnasium PointPush (OSRL)
Cost0.00e+0
48
Safe Reinforcement LearningSafety-Gymnasium AntVelocity OSRL
Cost0.00e+0
48
AntVelocitySafety Gym AntVelocity
Computation overhead (minutes)7.3
5
CarCircleSafety Gym CarCircle
Computation Overhead (minutes)9.2
5
PointGoalSafety Gym PointGoal
Computation Overhead (minutes)5.5
5
PointPushSafety Gym PointPush
Computation Overhead (minutes)6.3
5
Showing 8 of 8 rows

Other info

Follow for update