List your company

Safe Reinforcement Learning on Safety-Gymnasium PointGoal OSRL

2.3CostSafe-RULE (COptiDICE)
-8.09262.054132.2202.346Jun 8, 2026

Evaluation results

MethodLinks
Safe-RULE (COptiDICE)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.062.31.6
Safe-RULE (CPQ)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.063.57.9
Safe-RULE (CPQ)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.064.712.6
CPQAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.064.9-2.1
Safe-RULE (BEAR-Lag)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.064.912.1
Safe-RULE (CPQ)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.065.30.5
BEAR-LagAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.066.8-26.8
Safe-RULE (CPQ)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.067.20.7
Safe-RULE (BEAR-Lag)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.067.38.4
Safe-RULE (BEAR-Lag)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.068.14.9
Safe-RULE (BEAR-Lag)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.068.99.5
Safe-RULE (BCQ-Lag)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.069.49.1
Safe-RULE (CPQ)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.069.414.4
Safe-RULE (BEAR-Lag)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.0610.112.3
Safe-RULE (COptiDICE)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.0610.35.9
Safe-RULE (BEAR-Lag)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.0610.49.1
Safe-RULE (COptiDICE)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.0610.44.9
Safe-RULE (BCQ-Lag)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.0610.810.8
Safe-RULE (COptiDICE)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.0614.97.8
Safe-RULE (COptiDICE)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.0617.112.7
Safe-RULE (BCQ-Lag)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.0617.518.3
BCQ-LagAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0618.92.8
Safe-RULE (BCQ-Lag)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.0621.919.5
Safe-RULE (CPQ)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.0621.90.1
Safe-RULE (COptiDICE)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.0622.78.7
Safe-RULE (BCQ-Lag)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.0623.914.6
Safe-RULE (BCQ-Lag)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.0624.217.4
BEAR-LagAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.0627.910.5
BCQ-LagAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0630.619.1
BEAR-LagAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0630.86.3
BCQ-LagAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0631.113.9
CPQAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0632-0.7
BCQ-LagAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0632.621.4
BCQ-LagAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.0633.613.6
COptiDICEAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0636.6-9.1
CPQAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0642.10.1
CPQAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.0642.10.1
COptiDICEAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.0645.316.7
COptiDICEAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.0646.49
CPQAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.0652.9-1.9
CPQAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0654.60.3
COptiDICEAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0660.615.6
COptiDICEAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0664.314.2
BCQ-LagAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.066915.8
BEAR-LagAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0669.8-0.6
COptiDICEAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0670.313
BEAR-LagAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.062080
BEAR-LagAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.06262.11