Goal-Conditioned Reinforcement Learning on OGBench pointmaze-large-stitch v0
100Success RateCD
Evaluation Results
| Method | Links | |
|---|---|---|
| CDMode=Planning Method2025.10 | 100 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 93.9 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 93.2 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 92.2 | |
| QRLMode=Base Learner2025.10 | 88.8 | |
| OTA +TTGSMode=TTGS Augmented2025.10 | 69.8 | |
| OTAMode=Base Learner2025.10 | 64 | |
| SAWMode=Base Learner2025.10 | 41.2 | |
| GCIQLMode=Base Learner2025.10 | 29 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 29 | |
| HIQLMode=Base Learner2025.10 | 13.2 |