Offline Reinforcement Learning on hopper medium
3,729Normalized ScoreQDFM
Evaluation Results
| Method | Links | |
|---|---|---|
| QDFM2026.02 | 3,729 | |
| BCQ2026.02 | 3,618 | |
| AWBC2026.02 | 712 | |
| AWAC2026.02 | 154 | |
| CQL2026.02 | 113 | |
| GreedyQ2026.02 | 111 | |
| Q-ALIGN DT2026.05 | 102.1 | |
| DMG2026.02 | 100.6 | |
| TD3+BCSeeds=52023.10 | 98.4 | |
| DM2026.05 | 98.1 | |
| SAC-RND2026.02 | 97.8 | |
| COMBOSeeds=52023.10 | 97.2 | |
| Anti-exploration Method2026.02 | 97.1 | |
| CGDT2026.05 | 96.9 | |
| QT2026.05 | 96.9 | |
| QCS2026.05 | 96.4 | |
| ProposedSeeds=52023.10 | 94.9 | |
| OptiDICESeeds=52023.10 | 94.1 | |
| DC2026.05 | 92.5 | |
| LSDT2026.05 | 87.2 | |
| O-DICE2026.02 | 86.1 | |
| ATACSeeds=52023.10 | 85.6 | |
| GPC-SAC2026.02 | 82.9 | |
| I-TAPNoise=1.252026.02 | 74.6 | |
| CQLSeeds=52023.10 | 74.3 | |
| I-TAPNoise=3.752026.02 | 71.43 | |
| L-MAPNoise=1.252026.02 | 71.08 | |
| DT2026.05 | 67.6 | |
| L-MAPNoise=3.752026.02 | 66.68 | |
| QDTReward Specification=Step-wise2024.02 | 66.5 | |
| IQLSeeds=52023.10 | 66.3 | |
| IQL2026.02 | 66.2 | |
| IQL2026.05 | 63.8 | |
| I-TAPNoise=7.52026.02 | 60.88 | |
| DTReward Specification=Step-wise2024.02 | 60.3 | |
| DTNoise=1.252026.02 | 59.39 | |
| TD3+BC2026.05 | 59.3 | |
| CQLReward Specification=Step-wise2024.02 | 58 | |
| DTReward Specification=Final Return2024.02 | 57.3 | |
| DTNoise=3.752026.02 | 56.09 | |
| TD3-CVAE2026.02 | 55.9 | |
| L-MAPNoise=7.52026.02 | 55.26 | |
| BCQSeeds=52023.10 | 54.5 | |
| CQL2026.02 | 53 | |
| BEARSeeds=52023.10 | 52.1 | |
| DTNoise=7.52026.02 | 51.62 | |
| QDTReward Specification=Final Return2024.02 | 50.7 | |
| STCDynamics Shift=Gravity, Target Quality=medium2026.02 | 43.4 | |
| DARA2025.06 | 40.61 | |
| IQL2025.12 | 35.2 | |
| IQL2025.06 | 32.99 | |
| OTDFDynamics Shift=Gravity, Target Quality=medium2026.02 | 32.4 | |
| IGDF2025.12 | 31.6 | |
| DARA2025.12 | 25.5 | |
| OTDF2025.12 | 24.2 | |
| CQLReward Specification=Final Return2024.02 | 23.3 | |
| BOSA2025.12 | 20.6 | |
| DVDF-IGDF2025.12 | 20.3 | |
| DVDF-OTDF2025.12 | 19.3 | |
| DARADynamics Shift=Gravity, Target Quality=medium2026.02 | 17.3 | |
| IGDFDynamics Shift=Gravity, Target Quality=medium2026.02 | 15.3 | |
| BOSADynamics Shift=Gravity, Target Quality=medium2026.02 | 15.2 | |
| MOBODY2025.06 | 13.05 | |
| MOPO2025.06 | 12.96 | |
| TD3-BC2025.06 | 12.69 | |
| BOSA2025.06 | 12.67 | |
| SRPODynamics Shift=Gravity, Target Quality=medium2026.02 | 12.4 | |
| IQLDynamics Shift=Gravity, Target Quality=medium2026.02 | 11.2 |