ALFWorld
Aligned text-and-3D embodied environment - agents learn household tasks (pick & place, heat, cool, clean) as both TextWorld games and visually-rendered ALFRED scenes.
- Type
- RL Env
- Publisher
- MIT CSAIL
- Capabilities
- PlanningEmbodiedInstruction Following
- Runtime
gymnasium- License
- mit
- Size
- 3,553 expert-annotated tasks across 6 categories (pick_and_place, look_at_obj_in_light, pick_clean_then_place, pick_heat_then_place, pick_cool_then_place, pick_two_obj_and_place)
- Published
- Oct 2020
- Canonical
- github.com/alfworld/alfworld
Cite
Notes
Only stored in your browser.
Lift evidence
2Models
Compatible
any