Datasets › GSCAN

GSCAN (Grounded SCAN)

Introduced by Laura Ruis et al. in A Benchmark for Systematic Generalization in Grounded Language Understanding11 Mar 2020 archive 2025-07-28

Grounded SCAN poses a simple task, where an agent must execute action sequences based on a synthetic language instruction.

The agent is presented with a simple grid world containing a collection of objects, each of which is associated with a vector of features. The agent is evaluated on its ability to follow one or more instructions in this environment. Some instructions require interaction with particular kinds of objects.

[gSCAN Example]

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 22 papers for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT Licence

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

Variants archive 2025-07-28

  • GSCAN

1 variant name, as the archive lists them.

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