Loco-navigation Goal-conditioned Reinforcement Learning on antmaze expert
97Success RateSAW
Evaluation Results
| Method | Links | |
|---|---|---|
| SAWBackbone RL Algorithm=SAW, Test-time Training (TTT) variant=None (Pre-trained)2025.07 | 97 | |
| SAW + TTT (no critic)Backbone RL Algorithm=SAW, Test-time Training (TTT) variant=GC-TTT (no critic)2025.07 | 97 | |
| SAW + TTTBackbone RL Algorithm=SAW, Test-time Training (TTT) variant=GC-TTT2025.07 | 97 | |
| GC-IQL-DDPG + TTTBackbone RL Algorithm=GC-IQL-DDPG, Test-time Training (TTT) variant=GC-TTT2025.07 | 85 | |
| GC-IQL-DDPG + TTT (no critic)Backbone RL Algorithm=GC-IQL-DDPG, Test-time Training (TTT) variant=GC-TTT (no critic)2025.07 | 80 | |
| GC-IQL-DDPGBackbone RL Algorithm=GC-IQL-DDPG, Test-time Training (TTT) variant=None (Pre-trained)2025.07 | 64 | |
| GC-BC + TTT (no critic)Backbone RL Algorithm=GC-BC, Test-time Training (TTT) variant=GC-TTT (no critic)2025.07 | 54 | |
| GC-BC + TTTBackbone RL Algorithm=GC-BC, Test-time Training (TTT) variant=GC-TTT2025.07 | 48 | |
| GC-BCBackbone RL Algorithm=GC-BC, Test-time Training (TTT) variant=None (Pre-trained)2025.07 | 29 |