List your company
ResearchFormerly WizWand

Goal-conditioned Reinforcement Learning on manipulation cube-single-play

75Success RateGC-IQL-DDPG + TTT
2.221.14058.9Jul 24, 2025Aug 16, 2025Sep 9, 2025Oct 2, 2025Oct 26, 2025Nov 18, 2025Dec 12, 2025
Updated 5mo ago

Evaluation results

MethodLinks
GC-IQL-DDPG + TTTBackbone RL Algorithm=GC-IQL-DDPG, Test-time Training (TTT) variant=GC-TTT2025.0775
GC-IQL-DDPGBackbone RL Algorithm=GC-IQL-DDPG, Test-time Training (TTT) variant=None (Pre-trained)2025.0774
SAWBackbone RL Algorithm=SAW, Test-time Training (TTT) variant=None (Pre-trained)2025.0773
SAW + TTTBackbone RL Algorithm=SAW, Test-time Training (TTT) variant=GC-TTT2025.0771
CRL2025.1232
HIQL2025.1231
Eik-HIQL2025.1225
Eik-HiQRL2025.1212
QRL2025.1211
GC-BC + TTTBackbone RL Algorithm=GC-BC, Test-time Training (TTT) variant=GC-TTT2025.078
GC-BCBackbone RL Algorithm=GC-BC, Test-time Training (TTT) variant=None (Pre-trained)2025.075