Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Open paper
Benchmark
Model
Rank
Results
vision-and-language-navigation-on-vln-challenge
Self-Monitoring Navigation Agent (no beam search; Progress Inference)
#9
success: 0.48
length: 18.04
error: 5.67
oracle success: 0.59
…
Rank counts only results with a code link.