Offline Reinforcement Learning on Ant-Kinematic
90.34Normalized ScoreTABB
Evaluation Results
| Method | Links | |
|---|---|---|
| TABBSrc=medium-expert, Tar=expert2026.05 | 90.34 | |
| TABBSrc=medium-replay, Tar=expert2026.05 | 87.05 | |
| TABBSrc=medium, Tar=expert2026.05 | 83.67 | |
| MOBODYSrc=medium, Tar=expert2026.05 | 76.04 | |
| TABBSrc=medium-expert, Tar=medium-expert2026.05 | 67.91 | |
| TABBSrc=medium, Tar=medium-expert2026.05 | 65.1 | |
| TABBSrc=medium-replay, Tar=medium-expert2026.05 | 63.98 | |
| IQLSrc=medium, Tar=expert2026.05 | 59.6 | |
| MOBODYSrc=medium, Tar=medium-expert2026.05 | 59.12 | |
| IQLSrc=medium, Tar=medium-expert2026.05 | 57.8 | |
| TABBSrc=medium-replay, Tar=medium2026.05 | 54.44 | |
| DARASrc=medium, Tar=expert2026.05 | 54.2 | |
| DARASrc=medium, Tar=medium-expert2026.05 | 54.1 | |
| TABBSrc=medium, Tar=medium2026.05 | 53.87 | |
| TABBSrc=medium-expert, Tar=medium2026.05 | 51.7 | |
| MOBODYSrc=medium-expert, Tar=medium-expert2026.05 | 50.93 | |
| DROCOSrc=medium, Tar=medium-expert2026.05 | 50.86 | |
| MOBODYSrc=medium, Tar=medium2026.05 | 50.56 | |
| IQLSrc=medium, Tar=medium2026.05 | 50 | |
| IQLSrc=medium-expert, Tar=medium2026.05 | 49.5 | |
| MOBODYSrc=medium-expert, Tar=medium2026.05 | 47.72 | |
| DROCOSrc=medium, Tar=expert2026.05 | 46.89 | |
| DROCOSrc=medium, Tar=medium2026.05 | 46.04 | |
| BOSASrc=medium, Tar=expert2026.05 | 45.4 | |
| MOBODYSrc=medium-replay, Tar=medium2026.05 | 44.98 | |
| DARASrc=medium-expert, Tar=medium2026.05 | 44.7 | |
| DROCOSrc=medium-expert, Tar=medium2026.05 | 44.57 | |
| IQLSrc=medium-replay, Tar=medium2026.05 | 43.7 | |
| DARASrc=medium, Tar=medium2026.05 | 42.3 | |
| DARASrc=medium-replay, Tar=medium2026.05 | 42 | |
| DROCOSrc=medium-replay, Tar=medium2026.05 | 41.85 | |
| IQLSrc=medium-expert, Tar=medium-expert2026.05 | 37.2 | |
| MOBODYSrc=medium-replay, Tar=medium-expert2026.05 | 37 | |
| MOBODYSrc=medium-expert, Tar=expert2026.05 | 36.86 | |
| IQLSrc=medium-replay, Tar=medium-expert2026.05 | 36.5 | |
| DARASrc=medium-replay, Tar=medium-expert2026.05 | 36 | |
| DARASrc=medium-expert, Tar=medium-expert2026.05 | 33.3 | |
| BOSASrc=medium, Tar=medium-expert2026.05 | 31.7 | |
| DROCOSrc=medium-expert, Tar=medium-expert2026.05 | 29.71 | |
| DROCOSrc=medium-replay, Tar=medium-expert2026.05 | 29.26 | |
| DROCOSrc=medium-expert, Tar=expert2026.05 | 25.55 | |
| MOBODYSrc=medium-replay, Tar=expert2026.05 | 24.62 | |
| IQLSrc=medium-replay, Tar=expert2026.05 | 24.4 | |
| DROCOSrc=medium-replay, Tar=expert2026.05 | 22.88 | |
| DARASrc=medium-replay, Tar=expert2026.05 | 22.1 | |
| BOSASrc=medium, Tar=medium2026.05 | 20.9 | |
| BOSASrc=medium-replay, Tar=expert2026.05 | 19.5 | |
| BOSASrc=medium-replay, Tar=medium-expert2026.05 | 19.1 | |
| BOSASrc=medium-replay, Tar=medium2026.05 | 19 | |
| BOSASrc=medium-expert, Tar=medium2026.05 | 19 | |
| IQLSrc=medium-expert, Tar=expert2026.05 | 18.7 | |
| DARASrc=medium-expert, Tar=expert2026.05 | 17.8 | |
| BOSASrc=medium-expert, Tar=expert2026.05 | 14.5 | |
| BOSASrc=medium-expert, Tar=medium-expert2026.05 | 6.4 |