# World Model Control by Trajectory Reachability Metrics

arXiv: https://arxiv.org/abs/2605.22164 · HTML: https://mlsanity.com/paper/2605.22164/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 15 of 15)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [Visual Reinforcement Learning with Imagined Goals](https://mlsanity.com/paper/1807.04742/) (2018)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [Search on the Replay Buffer: Bridging Planning and Reinforcement Learning](https://mlsanity.com/paper/1906.05253/) (2019)
- [stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation](https://mlsanity.com/paper/2605.21800/) (2026)
- [Predictive but Not Plannable: RC-aux for Latent World Models](https://mlsanity.com/paper/2605.07278/) (2026)
- [Closing the Train-Test Gap in World Models for Gradient-Based Planning](https://mlsanity.com/paper/2512.09929/) (2025)
- [Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning](https://mlsanity.com/paper/2307.10846/) (2023)

## Built on by (most cited first, 8 of 8)

- [ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models](https://mlsanity.com/paper/2606.09028/) (2026)
- [Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models](https://mlsanity.com/paper/2607.23602/) (2026)
- [Reinforced Planning with Latent World Models](https://mlsanity.com/paper/2608.18669/) (2026)
- [The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom](https://mlsanity.com/paper/2608.10145/) (2026)
- [ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models](https://mlsanity.com/paper/2609.05461/) (2026)
- [Anisotropic Representations Improve Planning in JEPA World Models](https://mlsanity.com/paper/2609.37441/) (2026)
- [Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning](https://mlsanity.com/paper/2610.01224/) (2026)
- [When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models](https://mlsanity.com/paper/2610.05550/) (2026)

## Abstract (arXiv)

Latent world models can learn representations that contain information needed for control, while the downstream controller may still rank candidate actions poorly when it relies on terminal latent distance alone. We study this failure in a fixed encoder and introduce trajectory reachability metrics (TRM), a small temporal pairwise cost trained from logged trajectories and used to rank predicted endpoints of a candidate action sequence against a goal. In the TwoRoom evaluation on 100 episodes from a high distance range, the original controller with LeWorldModel reaches 7.0% mean success. Temporal TRM trained after excluding all evaluation episodes reaches 96.7%, shuffled label controls stay at 0.0%, and TRM also improves PLDM from 32.7% to 84.0%. TopoNav, a separate pixel navigation task, shows the same link between repaired ranking and closed loop control. The selection audit with shared candidates (SASC) and rowspace interventions show that the gain comes from reweighting latent directions carrying the action decision. The XY rowspace contributes less than 1% of terminal latent MSE but carries most of the information needed for control. Coverage and boundary tests define the scope. Balanced doorway coverage restores a 0.0% coverage failure to 100.0% success, while an unseen wall orientation and contact rich PushT expose layout, dynamics, and recovery limits.