Goal-Conditioned Reinforcement Learning on OGBench antmaze-giant-navigate v0
76Success RateGAS
Evaluation Results
| Method | Links | |
|---|---|---|
| GASMode=Planning Method2025.10 | 76 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 71 | |
| SAWMode=Base Learner2025.10 | 68.5 | |
| OTA +TTGSMode=TTGS Augmented2025.10 | 68.5 | |
| OTAMode=Base Learner2025.10 | 67.4 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 65.8 | |
| HIQLMode=Base Learner2025.10 | 65 | |
| QRLMode=Base Learner2025.10 | 11.8 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 10.8 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 5.4 | |
| GCIQLMode=Base Learner2025.10 | 0.4 |