Goal-Conditioned Reinforcement Learning on OGBench visual-antmaze-giant-stitch v0
51.9Success RateGAS
Evaluation Results
| Method | Links | |
|---|---|---|
| GASMode=Planning Method2025.10 | 51.9 | |
| OTA +TTGSMode=TTGS Augmented2025.10 | 35.2 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 32.2 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 31 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 6 | |
| OTAMode=Base Learner2025.10 | 2.2 | |
| HIQLMode=Base Learner2025.10 | 0.2 | |
| GCIQLMode=Base Learner2025.10 | 0 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 0 | |
| QRLMode=Base Learner2025.10 | 0 | |
| SAWMode=Base Learner2025.10 | 0 |