Offline Reinforcement Learning on walker2d medium
1,248Normalized ScoreQDFM
Evaluation Results
| Method | Links | |
|---|---|---|
| QDFM2026.02 | 1,248 | |
| BCQ2026.02 | 930 | |
| CQL2026.02 | 665 | |
| GreedyQ2026.02 | 659 | |
| AWBC2026.02 | 248 | |
| Q-ALIGN DT2026.05 | 94.7 | |
| DMG2026.02 | 92.4 | |
| SAC-RND2026.02 | 91.6 | |
| LAWMaction-conditioned data percentage=5%2025.12 | 91.4 | |
| ATACSeeds=52023.10 | 89.6 | |
| Anti-exploration Method2026.02 | 89.3 | |
| QT2026.05 | 88.8 | |
| QCS2026.05 | 88.2 | |
| GPC-SAC2026.02 | 87.6 | |
| O-DICE2026.02 | 84.9 | |
| DM2026.05 | 83.8 | |
| TD3+BC2026.05 | 83.7 | |
| COMBOSeeds=52023.10 | 81.9 | |
| TD3+BCSeeds=52023.10 | 81.7 | |
| LSDT2026.05 | 81 | |
| ProposedSeeds=52023.10 | 80.8 | |
| IQL2026.05 | 79.9 | |
| CQLReward Specification=Step-wise2024.02 | 79.2 | |
| DC2026.05 | 79.2 | |
| CGDT2026.05 | 79.1 | |
| IQLSeeds=52023.10 | 78.3 | |
| IQL2026.02 | 78.3 | |
| CQLSeeds=52023.10 | 77.2 | |
| I-TAPNoise=3.52026.02 | 76.56 | |
| L-MAPNoise=3.52026.02 | 75.77 | |
| DT2026.05 | 74 | |
| DTReward Specification=Step-wise2024.02 | 73.3 | |
| CQL2026.02 | 73.3 | |
| TD3+BCaction-conditioned data percentage=100%, variant=Oracle2025.12 | 71.5 | |
| C-LAPaction-conditioned data percentage=100%, variant=Oracle2025.12 | 71.1 | |
| DTReward Specification=Final Return2024.02 | 69.9 | |
| C-LAPaction-conditioned data percentage=5%2025.12 | 68.7 | |
| TD3-CVAE2026.02 | 68.2 | |
| QDTReward Specification=Step-wise2024.02 | 67.1 | |
| TD3+BCaction-conditioned data percentage=5%2025.12 | 64.7 | |
| IDM-TD3+BCaction-conditioned data percentage=5%2025.12 | 64.3 | |
| QDTReward Specification=Final Return2024.02 | 63.7 | |
| I-TAPNoise=9.52026.02 | 60.22 | |
| BEARSeeds=52023.10 | 59.1 | |
| L-MAPNoise=9.52026.02 | 55.96 | |
| I-TAPNoise=152026.02 | 54.6 | |
| BCQSeeds=52023.10 | 53.1 | |
| DTNoise=3.52026.02 | 51.89 | |
| L-MAPNoise=152026.02 | 50.1 | |
| DTNoise=9.52026.02 | 39.16 | |
| DTNoise=152026.02 | 30.69 | |
| DVDF-IGDF2025.12 | 24.3 | |
| DVDF-OTDF2025.12 | 23.7 | |
| OptiDICESeeds=52023.10 | 21.8 | |
| OTDF2025.12 | 19.3 | |
| IQL2025.12 | 16.4 | |
| DARA2025.12 | 15.8 | |
| IGDF2025.12 | 14.3 | |
| BOSA2025.12 | 10.6 | |
| CQLReward Specification=Final Return2024.02 | 0 | |
| AWAC2026.02 | -18 |