Goal-Conditioned Reinforcement Learning on OGBench visual-antmaze-large-explore v0
25.2Success RateOTA +TTGS
Evaluation Results
| Method | Links | |
|---|---|---|
| OTA +TTGSMode=TTGS Augmented2025.10 | 25.2 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 15.2 | |
| GASMode=Planning Method2025.10 | 15.1 | |
| OTAMode=Base Learner2025.10 | 3.6 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 0.8 | |
| HIQLMode=Base Learner2025.10 | 0 | |
| GCIQLMode=Base Learner2025.10 | 0 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 0 | |
| QRLMode=Base Learner2025.10 | 0 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 0 | |
| SAWMode=Base Learner2025.10 | 0 |