Goal-Conditioned Reinforcement Learning on OGBench antmaze-large-explore v0
91.8Success RateSAW +TTGS
Evaluation Results
| Method | Links | |
|---|---|---|
| SAW +TTGSMode=TTGS Augmented2025.10 | 91.8 | |
| GASMode=Planning Method2025.10 | 91 | |
| OTAMode=Base Learner2025.10 | 80.8 | |
| OTA +TTGSMode=TTGS Augmented2025.10 | 80.8 | |
| GCIQL +TTGSMode=TTGS Augmented2025.10 | 66.7 | |
| CDMode=Planning Method2025.10 | 27 | |
| HIQL +TTGSMode=TTGS Augmented2025.10 | 26.6 | |
| HIQLMode=Base Learner2025.10 | 2.4 | |
| SAWMode=Base Learner2025.10 | 1.9 | |
| GCIQLMode=Base Learner2025.10 | 0.2 | |
| QRLMode=Base Learner2025.10 | 0 | |
| QRL +TTGSMode=TTGS Augmented2025.10 | 0 |