Offline Reinforcement Learning on Halfcheetah-Morph
59.6Normalized ScoreTABB
Evaluation Results
| Method | Links | |
|---|---|---|
| TABBSrc=medium, Tar=expert2026.05 | 59.6 | |
| TABBSrc=medium-replay, Tar=expert2026.05 | 53.99 | |
| TABBSrc=medium-expert, Tar=expert2026.05 | 46.11 | |
| TABBSrc=medium-expert, Tar=medium2026.05 | 44.03 | |
| TABBSrc=medium, Tar=medium2026.05 | 43.99 | |
| TABBSrc=medium-replay, Tar=medium2026.05 | 43.95 | |
| TABBSrc=medium, Tar=medium-expert2026.05 | 43.13 | |
| TABBSrc=medium-replay, Tar=medium-expert2026.05 | 43.01 | |
| TABBSrc=medium-expert, Tar=medium-expert2026.05 | 42.55 | |
| MOBODYSrc=medium, Tar=medium2026.05 | 42.16 | |
| MOBODYSrc=medium-expert, Tar=medium2026.05 | 41.99 | |
| IQLSrc=medium-expert, Tar=medium2026.05 | 41.5 | |
| BOSASrc=medium-expert, Tar=medium2026.05 | 41.3 | |
| DROCOSrc=medium, Tar=medium2026.05 | 41.06 | |
| DROCOSrc=medium-expert, Tar=medium2026.05 | 40.92 | |
| DARASrc=medium-expert, Tar=medium2026.05 | 40.3 | |
| MOBODYSrc=medium-replay, Tar=medium2026.05 | 39.21 | |
| DARASrc=medium-replay, Tar=medium2026.05 | 35.6 | |
| BOSASrc=medium-replay, Tar=medium2026.05 | 35 | |
| BOSASrc=medium, Tar=medium-expert2026.05 | 33.6 | |
| DROCOSrc=medium, Tar=medium-expert2026.05 | 32.85 | |
| BOSASrc=medium-expert, Tar=medium-expert2026.05 | 32.1 | |
| DARASrc=medium, Tar=medium-expert2026.05 | 32 | |
| IQLSrc=medium, Tar=medium-expert2026.05 | 31.8 | |
| IQLSrc=medium-replay, Tar=medium2026.05 | 30.8 | |
| DARASrc=medium-expert, Tar=medium-expert2026.05 | 30.6 | |
| DROCOSrc=medium-expert, Tar=medium-expert2026.05 | 30.22 | |
| IQLSrc=medium, Tar=medium2026.05 | 30 | |
| MOBODYSrc=medium, Tar=medium-expert2026.05 | 29.94 | |
| MOBODYSrc=medium-expert, Tar=medium-expert2026.05 | 29.59 | |
| DARASrc=medium, Tar=medium2026.05 | 26.6 | |
| IQLSrc=medium-expert, Tar=medium-expert2026.05 | 25.8 | |
| MOBODYSrc=medium-replay, Tar=medium-expert2026.05 | 21.38 | |
| DROCOSrc=medium-replay, Tar=medium2026.05 | 20.49 | |
| BOSASrc=medium-replay, Tar=medium-expert2026.05 | 19.9 | |
| BOSASrc=medium, Tar=medium2026.05 | 19.3 | |
| DARASrc=medium-replay, Tar=medium-expert2026.05 | 16.9 | |
| IQLSrc=medium-replay, Tar=medium-expert2026.05 | 12.9 | |
| DARASrc=medium, Tar=expert2026.05 | 9.3 | |
| DROCOSrc=medium-expert, Tar=expert2026.05 | 9.29 | |
| BOSASrc=medium-expert, Tar=expert2026.05 | 9.1 | |
| DROCOSrc=medium-replay, Tar=medium-expert2026.05 | 8.56 | |
| IQLSrc=medium, Tar=expert2026.05 | 8.5 | |
| MOBODYSrc=medium, Tar=expert2026.05 | 8.41 | |
| DARASrc=medium-expert, Tar=expert2026.05 | 8.3 | |
| DROCOSrc=medium, Tar=expert2026.05 | 8.16 | |
| BOSASrc=medium, Tar=expert2026.05 | 7.9 | |
| IQLSrc=medium-expert, Tar=expert2026.05 | 7.8 | |
| MOBODYSrc=medium-expert, Tar=expert2026.05 | 7.36 | |
| IQLSrc=medium-replay, Tar=expert2026.05 | 5.9 | |
| MOBODYSrc=medium-replay, Tar=expert2026.05 | 4.7 | |
| DROCOSrc=medium-replay, Tar=expert2026.05 | 4.32 | |
| DARASrc=medium-replay, Tar=expert2026.05 | 3.7 | |
| BOSASrc=medium-replay, Tar=expert2026.05 | 2.4 |