List your company

Safe Reinforcement Learning on Safety-Gymnasium CarCircle OSRL

0CostSafe-RULE (CPQ)
-7.83645.05797.95150.843Jun 8, 2026

Evaluation results

MethodLinks
Safe-RULE (CPQ)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.060381.3
CPQAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.060284.6
Safe-RULE (CPQ)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.060381.1
CPQAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.060364.9
Safe-RULE (CPQ)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.060380.3
Safe-RULE (CPQ)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.060306.6
Safe-RULE (CPQ)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.060.7345.2
Safe-RULE (BEAR-Lag)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.062313.8
Safe-RULE (BEAR-Lag)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.062.9388.5
Safe-RULE (BEAR-Lag)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.063.9352.7
Safe-RULE (CPQ)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.064.4294.2
Safe-RULE (BEAR-Lag)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.065.9321.6
Safe-RULE (BEAR-Lag)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.067363.9
Safe-RULE (BCQ-Lag)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.069414
Safe-RULE (BEAR-Lag)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.069.8356
Safe-RULE (BCQ-Lag)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.0610.2314
Safe-RULE (COptiDICE)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.0610.6176.9
Safe-RULE (COptiDICE)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.0611.5167.6
Safe-RULE (COptiDICE)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.0613.1157.7
Safe-RULE (COptiDICE)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.0618.6147
Safe-RULE (COptiDICE)Attack=Max Reward, Poison Ratio=15%, Unlearning Status=After2026.0619.4144.9
Safe-RULE (BCQ-Lag)Attack=Min Reward, Poison Ratio=15%, Unlearning Status=After2026.0621.7301.4
Safe-RULE (BCQ-Lag)Attack=Min Reward, Poison Ratio=5%, Unlearning Status=After2026.0622.4312.8
BCQ-LagAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0627.1130.6
Safe-RULE (BCQ-Lag)Attack=Max Reward, Poison Ratio=5%, Unlearning Status=After2026.0627.8388.6
Safe-RULE (BCQ-Lag)Attack=Max Cost, Poison Ratio=15%, Unlearning Status=After2026.0634.4365.4
Safe-RULE (COptiDICE)Attack=Max Cost, Poison Ratio=5%, Unlearning Status=After2026.0638.3175
CPQAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0652.4366.7
BEAR-LagAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0656.2333.1
BEAR-LagAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0658.9337.9
BCQ-LagAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.0662.5251.1
BEAR-LagAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0664.6447.4
BCQ-LagAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0664.9396.3
BEAR-LagAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0668.3199
COptiDICEAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.0669.3239
CPQAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0673.9-159.3
COptiDICEAttack=Max Reward, Poison Ratio=5%, Unlearning Status=Before2026.0675.2262.6
BEAR-LagAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.0679.1466.6
BCQ-LagAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0683.9322.2
COptiDICEAttack=Min Reward, Poison Ratio=15%, Unlearning Status=Before2026.0684.4-64.7
BCQ-LagAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0688.8285.2
COptiDICEAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.0690.7209.8
BEAR-LagAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.0694.1437.5
COptiDICEAttack=Max Cost, Poison Ratio=5%, Unlearning Status=Before2026.0694.1190.9
COptiDICEAttack=Max Reward, Poison Ratio=15%, Unlearning Status=Before2026.0697.2169.9
CPQAttack=Min Reward, Poison Ratio=5%, Unlearning Status=Before2026.06134.8-50.2
BCQ-LagAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.06136.2331
CPQAttack=Max Cost, Poison Ratio=15%, Unlearning Status=Before2026.06195.9173.8