Loco-navigation Goal-conditioned Reinforcement Learning on humanoidmaze play
84Success RateSAW + TTT
Evaluation Results
| Method | Links | |
|---|---|---|
| SAW + TTTBackbone RL Algorithm=SAW, Test-time Training (TTT) variant=GC-TTT2025.07 | 84 | |
| SAWBackbone RL Algorithm=SAW, Test-time Training (TTT) variant=None (Pre-trained)2025.07 | 78 | |
| GC-BC + TTTBackbone RL Algorithm=GC-BC, Test-time Training (TTT) variant=GC-TTT2025.07 | 68 | |
| GC-IQL-DDPG + TTTBackbone RL Algorithm=GC-IQL-DDPG, Test-time Training (TTT) variant=GC-TTT2025.07 | 49 | |
| GC-BCBackbone RL Algorithm=GC-BC, Test-time Training (TTT) variant=None (Pre-trained)2025.07 | 33 | |
| GC-IQL-DDPGBackbone RL Algorithm=GC-IQL-DDPG, Test-time Training (TTT) variant=None (Pre-trained)2025.07 | 10 |