# IMWM: Intuition Models Complement World Models for Latent Planning

arXiv: https://arxiv.org/abs/2606.01626 · HTML: https://mlsanity.com/paper/2606.01626/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [Deep Dynamics Models for Learning Dexterous Manipulation](https://mlsanity.com/paper/1909.11652/) (2019)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [Imagination-Augmented Agents for Deep Reinforcement Learning](https://mlsanity.com/paper/1707.06203/) (2017)
- [Parrot: Data-Driven Behavioral Priors for Reinforcement Learning](https://mlsanity.com/paper/2011.10024/) (2020)
- [Value Prediction Network](https://mlsanity.com/paper/1707.03497/) (2017)
- [Model-Free Episodic Control](https://mlsanity.com/paper/1606.04460/) (2016)
- [Objective Mismatch in Model-based Reinforcement Learning](https://mlsanity.com/paper/2002.04523/) (2020)
- [Sample-efficient Cross-Entropy Method for Real-time Planning](https://mlsanity.com/paper/2008.06389/) (2020)
- [The Predictron: End-To-End Learning and Planning](https://mlsanity.com/paper/1612.08810/) (2016)
- [On the role of planning in model-based deep reinforcement learning](https://mlsanity.com/paper/2011.04021/) (2020)
- [Information asymmetry in KL-regularized RL](https://mlsanity.com/paper/1905.01240/) (2019)
- [Retrieval-Augmented Reinforcement Learning](https://mlsanity.com/paper/2202.08417/) (2022)
- [Skill-based Model-based Reinforcement Learning](https://mlsanity.com/paper/2207.07560/) (2022)
- [Behavior Priors for Efficient Reinforcement Learning](https://mlsanity.com/paper/2010.14274/) (2020)
- [Data-driven Planning via Imitation Learning](https://mlsanity.com/paper/1711.06391/) (2017)
- [Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization](https://mlsanity.com/paper/2004.08763/) (2020)
- [Retrieval-Augmented Decision Transformer: External Memory for In-context RL](https://mlsanity.com/paper/2410.07071/) (2024)

## Built on by (most cited first, 4 of 4)

- [QQWorld: Quantile-Quantile Matching for World Model Regularization](https://mlsanity.com/paper/2607.28415/) (2026)
- [Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel](https://mlsanity.com/paper/2607.12547/) (2026)
- [Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think](https://mlsanity.com/paper/2609.30036/) (2026)
- [Beyond a single latent space: a dual-latent world model for long-horizon planning](https://mlsanity.com/paper/2609.37644/) (2026)

## Abstract (arXiv)

Planning with a learned latent world model is a promising route to control from raw pixels, but a strong world model alone is not enough. We show this experimentally: even with a perfect world model (operationalized by replacing the learned forward predictor with an idealized rollout of the true environment dynamics), a finite-budget sample-based planner still fails on some tasks, indicating that the bottleneck can lie in search rather than in world-model accuracy. Motivated by this gap, we propose IMWM (Intuition Model + World Model), which pairs the world model with an intuition model trained from demonstrations to recognize promising actions. The two models collaborate through three lightweight components: (i) Retrieval Initialization, which initializes the planner's action proposal from a retrieved demonstration; (ii) Hybrid Cost, which combines the intuition score with the world-model rollout cost; and (iii) a Reliability Gate, which adjusts how much the planner trusts intuition in each setting. Across four pixel-based goal-reaching tasks (Two-Room, Reacher, Push-T, and OGBench-Cube), IMWM has higher mean success than the world-model-only planner on all four, with the largest gains on Two-Room (99.2%, +11.5 percentage points) and OGBench-Cube (94.7%, +28.5 percentage points).