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

- Source: arXiv cs.RO
- Published: 2026-10-19T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/xtvnmj4vt05be1lj91vjxnbou
- Original: https://arxiv.org/abs/2606.06832

## Summary

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).