Environment-Agnostic Multitask Learning

Reported on 5 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots5 results

Vision and Language NavigationonVLN Challenge
error· 2020-03-01
6.03
best: 1.61 (human)
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation arXiv:2003.00443
Vision and Language NavigationonVLN Challenge
length· 2020-03-01
13.35
best: 1257.38 (Speaker-Follower)
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation arXiv:2003.00443
Vision and Language NavigationonVLN Challenge
oracle success· 2020-03-01
0.56
best: 1 (FOAM-Beam Search)
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation arXiv:2003.00443
Vision and Language NavigationonVLN Challenge
spl· 2020-03-01
0.4
best: 0.76 (human)
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation arXiv:2003.00443
Vision and Language NavigationonVLN Challenge
success· 2020-03-01
0.45
best: 0.86 (human)
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation arXiv:2003.00443