Papers › VALAN: Vision and Language Agent Navigation

VALAN: Vision and Language Agent Navigation

6 Dec 2019arXiv:1912.03241archive 2025-07-28

Larry Lansing, Vihan Jain, Harsh Mehta, Haoshuo Huang, Eugene Ie

VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded language understanding tasks, such as Vision-and-Language Navigation and Vision-and-Dialog Navigation, in photo-realistic environments, such as Matterport3D and Google StreetView. We have added a minimal set of abstractions on top of SEED RL allowing us to generalize the architecture to solve a variety of other RL problems. In this article, we will describe VALAN's software abstraction and architecture, and also present an example of using VALAN to design agents for instruction-conditioned indoor navigation.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

google-research/valan officialmentioned in papermentioned on GitHubtf report

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

Deep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)Vision and Language Navigationreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SEED RL

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