Papers › Environment-agnostic Multitask Learning for Natural Language Grounded Navigation
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation
Xin Eric Wang, Vihan Jain, Eugene Ie, William Yang Wang, Zornitsa Kozareva, Sujith Ravi
Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e.g., following natural language instructions or dialog. However, existing methods tend to overfit training data in seen environments and fail to generalize well in previously unseen environments. To close the gap between seen and unseen environments, we aim at learning a generalized navigation model from two novel perspectives: (1) we introduce a multitask navigation model that can be seamlessly trained on both Vision-Language Navigation (VLN) and Navigation from Dialog History (NDH) tasks, which benefits from richer natural language guidance and effectively transfers knowledge across tasks; (2) we propose to learn environment-agnostic representations for the navigation policy that are invariant among the environments seen during training, thus generalizing better on unseen environments. Extensive experiments show that environment-agnostic multitask learning significantly reduces the performance gap between seen and unseen environments, and the navigation agent trained so outperforms baselines on unseen environments by 16% (relative measure on success rate) on VLN and 120% (goal progress) on NDH. Our submission to the CVDN leaderboard establishes a new state-of-the-art for the NDH task on the holdout test set. Code is available at https://github.com/google-research/valan.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Vision and Language Navigation | VLN Challenge | Environment-Agnostic Multitask Learning | error | 6.03 | #122 of 145 | Archive leaderboard | report |
| Vision and Language Navigation | VLN Challenge | Environment-Agnostic Multitask Learning | length | 13.35 | #122 of 145 | Archive leaderboard | report |
| Vision and Language Navigation | VLN Challenge | Environment-Agnostic Multitask Learning | oracle success | 0.56 | #122 of 145 | Archive leaderboard | report |
| Vision and Language Navigation | VLN Challenge | Environment-Agnostic Multitask Learning | spl | 0.4 | #122 of 145 | Archive leaderboard | report |
| Vision and Language Navigation | VLN Challenge | Environment-Agnostic Multitask Learning | success | 0.45 | #122 of 145 | Archive leaderboard | report |
| Visual Navigation | Cooperative Vision-and-Dialogue Navigation | Environment-agnostic Multitask Learning | dist_to_end_reduction | 3.91 | #7 of 19 | Archive leaderboard | report |
| Visual Navigation | Cooperative Vision-and-Dialogue Navigation | Environment-agnostic Multitask Learning | spl | 0.17 | #7 of 19 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections