Article

STRIPS-WM: Learning Grounded Propositional STRIPS-Style World Models from Image Transitions

A paper accepted to CoRL 2026 proposes the STRIPS-WM framework, which learns grounded STRIPS-style world models solely from image transitions (the current image, the executed high-level action, and the resulting image).

Part of the event: STRIPS-WM: Learning STRIPS-Style World Models from Image-Only Transitions

This page provides a summary and source link only.