Offline Reinforcement Learning on Adroit
137.7Adroit Mean ScorePBRL
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PBRL2026.02 | 137.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OURS2026.02 | 119.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPC-SAC2026.02 | 118.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| IQL2026.02 | 117.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CQL2026.02 | 107 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Doctor2025.08 | 100.2 | — | — | — | — | — | — | — | — | — | — | — | — | 85.7 | 4.9 | 9.6 | |
| MTM2025.08 | 96.5 | — | — | — | — | — | — | — | — | — | — | — | — | 80.5 | 5.5 | 10.5 | |
| IQL2025.08 | 88.3 | — | — | — | — | — | — | — | — | — | — | — | — | 83.3 | 3.2 | 1.8 | |
| DT2025.08 | 75.1 | — | — | — | — | — | — | — | — | — | — | — | — | 65.2 | 2 | 7.9 | |
| BC2025.08 | 56.6 | — | — | — | — | — | — | — | — | — | — | — | — | 56.1 | 0.5 | 0 | |
| PSSA2025.04 | 48.6 | 122 | 105.2 | 127.2 | 108.4 | 75.7 | 0.2 | 0.2 | 0 | 44.8 | 0 | 0.2 | -0.2 | — | — | — | |
| TSSA2025.04 | 47.9 | 104.6 | 105 | 126.4 | 106.3 | 89.7 | 0.4 | 0.4 | 0 | 41.1 | 0.4 | 0.2 | -0.2 | — | — | — | |
| FCNet2025.04 | 41 | 108 | 102.9 | 121.1 | 50 | 57.7 | 0.4 | 1.2 | 0 | 50.4 | -0.2 | 0.2 | -0.2 | — | — | — | |
| CQL2025.04 | 40.3 | 107 | 101.5 | 86.7 | 95 | 37.5 | 9.9 | 4.4 | 0.2 | 39.2 | 0.4 | 2.1 | -0.1 | — | — | — | |
| BC2025.04 | 36.7 | 85.1 | 34.9 | 125.6 | 101.3 | 34.4 | 0.5 | 1.5 | 0 | 56.9 | -0.1 | 0.8 | -0.1 | — | — | — | |
| DT2025.04 | 27.8 | 110.4 | 95.5 | 89.7 | 15.3 | -0.2 | 0.1 | 0.3 | 0.2 | 22.7 | 0.1 | 0.3 | -0.3 | — | — | — | |
| SpikeBert2025.04 | 21.1 | 46.2 | 96.4 | 71.3 | 0.3 | 20 | 0.2 | 0.3 | 0 | 17.6 | 0.2 | 0.3 | 0 | — | — | — | |
| SpikeGPT2025.04 | 16.3 | 30.5 | 65.3 | 51.1 | 0.7 | 29.8 | 0.1 | 0.3 | 0.1 | 17 | 0.2 | 0.3 | 0.1 | — | — | — | |
| CQL2025.08 | 7.8 | — | — | — | — | — | — | — | — | — | — | — | — | 5.4 | 1.9 | 0.5 | |
| TD3+BC2025.08 | 5.4 | — | — | — | — | — | — | — | — | — | — | — | — | 5.1 | 0.1 | 0.2 |