Goal-Conditioned Reinforcement Learning on OGBench antmaze-giant-stitch v0
86.2Success RateGAS
Evaluation Results
| Method | Links | |
|---|---|---|
| GASMode=Planning Method2025.10 | 86.2 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 78.6 | |
| OTA +TTGSMode=TTGS Augmented2025.10 | 71 | |
| CDMode=Planning Method2025.10 | 65 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 52.2 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 36.8 | |
| OTAMode=Base Learner2025.10 | 35.2 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 32.7 | |
| QRLMode=Base Learner2025.10 | 2 | |
| HIQLMode=Base Learner2025.10 | 1.4 | |
| GCIQLMode=Base Learner2025.10 | 0 | |
| SAWMode=Base Learner2025.10 | 0 |