List your company
ResearchFormerly WizWand

Goal-conditioned Reinforcement Learning on pointmaze navigate medium

99Success RateEik-HiQRL
-3.9622.7749.576.23Oct 8, 2025Oct 18, 2025Oct 29, 2025Nov 9, 2025Nov 20, 2025Dec 1, 2025Dec 12, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Eik-HiQRL2025.1299
Eik-HIQL2025.1293
HIQL2025.1292
QRL2025.1283
OrigDownstream algorithm=GCIVL, Observation type=State-based2025.1078
Dual Goal RepresentationsDownstream algorithm=GCIVL, Observation type=State-based2025.1076
VIBDownstream algorithm=GCIVL, Observation type=State-based2025.1069
CRL2025.1254
BYOL-γDownstream algorithm=GCIVL, Observation type=State-based2025.1037
TRADownstream algorithm=GCIVL, Observation type=State-based2025.103
VIPDownstream algorithm=GCIVL, Observation type=State-based2025.100