Goal-Conditioned Reinforcement Learning on OGBench pointmaze-large-navigate v0
92Success RateQRL +TTGS
Evaluation Results
| Method | Links | |
|---|---|---|
| QRL +TTGSMode=TTGS Augmented2025.10 | 92 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 88.1 | |
| OTA +TTGSMode=TTGS Augmented2025.10 | 87.7 | |
| OTAMode=Base Learner2025.10 | 85.1 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 83.6 | |
| QRLMode=Base Learner2025.10 | 82.4 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 78 | |
| SAWMode=Base Learner2025.10 | 78 | |
| HIQLMode=Base Learner2025.10 | 45.2 | |
| GCIQLMode=Base Learner2025.10 | 32.2 |