Goal-Conditioned Reinforcement Learning on OGBench humanoidmaze-giant-stitch v0
88.8Success RateOTA +TTGS
Evaluation Results
| Method | Links | |
|---|---|---|
| OTA +TTGSMode=TTGS Augmented2025.10 | 88.8 | |
| GASMode=Planning Method2025.10 | 82.4 | |
| OTAMode=Base Learner2025.10 | 81.6 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 79.8 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 78.1 | |
| CDMode=Planning Method2025.10 | 67 | |
| HIQLMode=Base Learner2025.10 | 4.4 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 4.1 | |
| QRLMode=Base Learner2025.10 | 0.5 | |
| GCIQLMode=Base Learner2025.10 | 0.2 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 0.2 | |
| SAWMode=Base Learner2025.10 | 0 |