List your company

Safe Reinforcement Learning on Safety-Gymnasium AntVelocity OSRL

0CostCPQ
-20.812119.669260.15400.631Jun 8, 2026

Evaluation results

MethodLinks
CPQAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.060-3,000.1
CPQAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.060-2,999.7
CPQAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.060-2,998.6
CPQAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.060-2,999.4
CPQAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.060-2,997.2
CPQAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.060-2,999
Safe-RULE (CPQ)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.0601,188.5
BEAR-LagAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.060-309.4
BEAR-LagAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.060-485.4
Safe-RULE (BEAR-Lag)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.0602,289.6
Safe-RULE (COptiDICE)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.0602,257.8
Safe-RULE (CPQ)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.060.11,966.5
BEAR-LagAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.060.1839.6
Safe-RULE (CPQ)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.060.4932.9
Safe-RULE (CPQ)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.061.51,242.3
Safe-RULE (CPQ)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.061.51,403.7
Safe-RULE (BEAR-Lag)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.062.32,534.7
Safe-RULE (COptiDICE)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.062.42,380
BCQ-LagAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.065.12,678.4
Safe-RULE (BEAR-Lag)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.065.72,531.5
Safe-RULE (COptiDICE)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.065.72,501.5
Safe-RULE (BEAR-Lag)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.065.82,517.8
Safe-RULE (BEAR-Lag)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.066.72,493
Safe-RULE (BCQ-Lag)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.066.82,135.2
Safe-RULE (COptiDICE)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.067.32,416
Safe-RULE (COptiDICE)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.067.82,428.2
Safe-RULE (CPQ)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.068.21,339.9
Safe-RULE (BEAR-Lag)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.068.52,616.2
Safe-RULE (COptiDICE)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.068.92,319.1
Safe-RULE (BCQ-Lag)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.069.31,829.1
Safe-RULE (BCQ-Lag)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.0610.11,800.5
Safe-RULE (BCQ-Lag)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.0619.72,787.9
Safe-RULE (BCQ-Lag)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.0621.42,962
Safe-RULE (BCQ-Lag)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.0636.22,570.8
COptiDICEAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.0639.81,260.6
COptiDICEAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0643.9851.9
COptiDICEAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0646.11,533.1
BCQ-LagAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0650.82,984.9
BEAR-LagAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0660.52,660.2
BCQ-LagAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.0674.22,898.4
BCQ-LagAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.06893,018.9
COptiDICEAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0690.22,942.6
BCQ-LagAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0694.82,603.1
BEAR-LagAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.06101.3544.4
COptiDICEAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.061082,941.9
BCQ-LagAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.06123.92,781.7
COptiDICEAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.06140.22,997.3
BEAR-LagAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.06520.32,738.2