Goal-Conditioned Reinforcement Learning on OGBench antmaze-large-navigate v0
93.2Success RateGAS
Evaluation Results
| Method | Links | |
|---|---|---|
| GASMode=Planning Method2025.10 | 93.2 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 92.3 | |
| OTA +TTGSMode=TTGS Augmented2025.10 | 91.6 | |
| OTAMode=Base Learner2025.10 | 91.4 | |
| HIQLMode=Base Learner2025.10 | 90.6 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 89.6 | |
| SAWMode=Base Learner2025.10 | 88.8 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 77 | |
| QRLMode=Base Learner2025.10 | 74 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 57.2 | |
| GCIQLMode=Base Learner2025.10 | 35.8 |