Safe Reinforcement Learning on Safety-Gymnasium PointGoal OSRL
2.3Cost
Safe-RULE (COptiDICE)
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 2.3 | 1.6 | |
2026.06 | 3.5 | 7.9 | |
2026.06 | 4.7 | 12.6 | |
2026.06 | 4.9 | -2.1 | |
2026.06 | 4.9 | 12.1 | |
2026.06 | 5.3 | 0.5 | |
2026.06 | 6.8 | -26.8 | |
2026.06 | 7.2 | 0.7 | |
2026.06 | 7.3 | 8.4 | |
2026.06 | 8.1 | 4.9 | |
2026.06 | 8.9 | 9.5 | |
2026.06 | 9.4 | 9.1 | |
2026.06 | 9.4 | 14.4 | |
2026.06 | 10.1 | 12.3 | |
2026.06 | 10.3 | 5.9 | |
2026.06 | 10.4 | 9.1 | |
2026.06 | 10.4 | 4.9 | |
2026.06 | 10.8 | 10.8 | |
2026.06 | 14.9 | 7.8 | |
2026.06 | 17.1 | 12.7 | |
2026.06 | 17.5 | 18.3 | |
2026.06 | 18.9 | 2.8 | |
2026.06 | 21.9 | 19.5 | |
2026.06 | 21.9 | 0.1 | |
2026.06 | 22.7 | 8.7 | |
2026.06 | 23.9 | 14.6 | |
2026.06 | 24.2 | 17.4 | |
2026.06 | 27.9 | 10.5 | |
2026.06 | 30.6 | 19.1 | |
2026.06 | 30.8 | 6.3 | |
2026.06 | 31.1 | 13.9 | |
2026.06 | 32 | -0.7 | |
2026.06 | 32.6 | 21.4 | |
2026.06 | 33.6 | 13.6 | |
2026.06 | 36.6 | -9.1 | |
2026.06 | 42.1 | 0.1 | |
2026.06 | 42.1 | 0.1 | |
2026.06 | 45.3 | 16.7 | |
2026.06 | 46.4 | 9 | |
2026.06 | 52.9 | -1.9 | |
2026.06 | 54.6 | 0.3 | |
2026.06 | 60.6 | 15.6 | |
2026.06 | 64.3 | 14.2 | |
2026.06 | 69 | 15.8 | |
2026.06 | 69.8 | -0.6 | |
2026.06 | 70.3 | 13 | |
2026.06 | 208 | 0 | |
2026.06 | 262.1 | 1 |