Continuous Control on BLOCKPUSH
0.88Success RateLC-DP
Evaluation Results
| Method | Links | |
|---|---|---|
| LC-DPFamily=Language-critique (DP), Supervision=Language labels2026.07 | 0.88 | |
| EDPFamily=Diffusion-based, Supervision=Scalar rewards2026.07 | 0.82 | |
| LC-BCFamily=Language-critique (BC), Supervision=Language labels2026.07 | 0.472 | |
| TD3+BCFamily=Policy-regularized, Supervision=Scalar rewards2026.07 | 0.412 | |
| DTFamily=Sequence-modeling, Supervision=Scalar rewards2026.07 | 0.024 | |
| CQLFamily=Value-based, Supervision=Scalar rewards2026.07 | 0 |