# Gradient-based Planning for World Models at Longer Horizons

> **Platform:** [SPIDITS AI](https://spidits.com/) — Real-Time AI News & Market Intelligence  
> **Published:** 2026-04-20T09:00:00.000Z  
> **Category:** PRODUCT_LAUNCH  
> **Impact Score:** 130/100  
> **Primary Source:** [BAIR Blog](http://bair.berkeley.edu/blog/2026/04/20/grasp)  
> **Canonical Citation:** [https://spidits.com/timeline/gradient-based-planning-for-world-models-at-longer-horizons](https://spidits.com/timeline/gradient-based-planning-for-world-models-at-longer-horizons)

## Executive Summary
GRASP is a new gradient-based planner for learned dynamics (a "world model") that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3).

## Referenced Coverage & Sources
- **[BAIR Blog](http://bair.berkeley.edu/blog/2026/04/20/grasp)**: Gradient-based Planning for World Models at Longer Horizons — _GRASP is a new gradient-based planner for learned dynamics (a "world model") that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3)..._

---
*Synthesized by SPIDITS AI Market Intelligence Desk. Track live AI news, model releases, and funding: [https://spidits.com](https://spidits.com)*