Goal-Conditioned Reinforcement Learning on OGBench humanoidmaze-large-navigate v0
86.4Success RateOTA +TTGS
Evaluation Results
| Method | Links | |
|---|---|---|
| OTA +TTGSMode=TTGS Augmented2025.10 | 86.4 | |
| GASMode=Planning Method2025.10 | 84.6 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 79.4 | |
| OTAMode=Base Learner2025.10 | 78.8 | |
| SAW +TTGSMode=TTGS Augmented2025.10 | 64.3 | |
| HIQLMode=Base Learner2025.10 | 48 | |
| SAWMode=Base Learner2025.10 | 46.8 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 10 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 8.4 | |
| QRLMode=Base Learner2025.10 | 6.8 | |
| GCIQLMode=Base Learner2025.10 | 2.1 |