Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Goal-Conditioned Reinforcement Learning on OGBench humanoidmaze-large-navigate v0

86.4Success Rate

OTA +TTGS

-1.27221.48944.2567.011Oct 8, 2025
Updated 8d ago

Evaluation Results

MethodLinks
2025.10
86.4
2025.10
84.6
2025.10
79.4
2025.10
78.8
2025.10
64.3
2025.10
48
2025.10
46.8
2025.10
10
2025.10
8.4
2025.10
6.8
2025.10
2.1