What Must a World Model Distinguish for Planning?
cs.LG, cs.RO
Submitted: 2026-09-26
Updated: 2026-09-26
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: World models simulate the consequences of action candidates, but good planning need not preserve every physical distinction required for accurate prediction.
Terminology
Abstract
World models simulate the consequences of action candidates, but good planning need not preserve every physical distinction required for accurate prediction. We formalize this gap through a hierarchy of mechanism, response, and decision sufficiency. Given a candidate set, the planning query determines which physical variations matter and how precisely they must be preserved: coarse decisions can discard much of the information needed for prediction, whereas fine decisions may require nearly the same resolution. In practice, planners often adaptively search to construct candidates, and information unnecessary for final selection may still be needed to discover good candidates. What a world model must preserve therefore depends on the query, the candidate set, and the planner. We study these effects in a collision system, nonlinear dynamics, and robotic planning. These varying requirements raise a design question: where should query information enter the planning system? A model that jointly generates actions and outcomes conditioned on the query achieves lower regret than an action-conditioned world model on seen objectives, but this advantage largely disappears when generalizing to unseen objectives. Motivated by this, we propose a modular design in which the query determines where to look and an action-conditioned model predicts what will happen, allowing the same predictions to be reused across objectives.
Sources
- Deep Variational Information Bottleneck
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning
- Metrics for Finite Markov Decision Processes
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Temporal Difference Learning for Model Predictive Control
- Representation Learning in Deep RL via Discrete Information Bottleneck
- Objective Mismatch in Model-based Reinforcement Learning
- DINOv2: Learning Robust Visual Features without Supervision
- ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
- Motubrain: An Advanced World Action Model for Robot Control
- What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
- Physically Viable World Models: A Case for Query-Conditioned Embodied AI
- World Action Models are Zero-shot Policies
- Learning Invariant Representations for Reinforcement Learning without Reconstruction
- World Action Planner: Generalizable Robot Decision-Making with Action-Conditioned World Models
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks