# Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection

arXiv: https://arxiv.org/abs/2608.06706 · HTML: https://mlsanity.com/paper/2608.06706/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 45 of its 51 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 30 of 45)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Unsupervised State Representation Learning in Atari](https://mlsanity.com/paper/1906.08226/) (2019)
- [Learning to Act without Actions](https://mlsanity.com/paper/2312.10812/) (2023)
- [The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels](https://mlsanity.com/paper/2101.02722/) (2021)
- [DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations](https://mlsanity.com/paper/2110.14565/) (2021)
- [Causal Influence Detection for Improving Efficiency in Reinforcement Learning](https://mlsanity.com/paper/2106.03443/) (2021)
- [Denoised MDPs: Learning World Models Better Than the World Itself](https://mlsanity.com/paper/2206.15477/) (2022)
- [Learning Task Informed Abstractions](https://mlsanity.com/paper/2106.15612/) (2021)
- [Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models](https://mlsanity.com/paper/2205.13817/) (2022)
- [Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models](https://mlsanity.com/paper/2207.08229/) (2022)
- [DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control](https://mlsanity.com/paper/2409.12192/) (2024)
- [Latent Action Learning Requires Supervision in the Presence of Distractors](https://mlsanity.com/paper/2502.00379/) (2025)
- [Provable RL with Exogenous Distractors via Multistep Inverse Dynamics](https://mlsanity.com/paper/2110.08847/) (2021)
- [INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL](https://mlsanity.com/paper/2204.08585/) (2022)
- [Learning Latent Dynamic Robust Representations for World Models](https://mlsanity.com/paper/2405.06263/) (2024)
- [Sensorimotor World Models: Perception for Action via Inverse Dynamics](https://mlsanity.com/paper/2606.20104/) (2026)

## Built on by (most cited first, 2 of 2)

- [Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models](https://mlsanity.com/paper/2610.04539/) (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 plan by predicting future states from an action, but when a scene contains motion the agent does not control, they quietly go action-blind: predictions for different actions become indistinguishable even as the training loss keeps improving. Existing remedies suppress this distraction with reconstruction, task reward, or auxiliary objectives, each adding machinery or assumptions. We show that a minimal alternative suffices, borrowed from the dueling decomposition of value into a state baseline and an action advantage: in latent dynamics, subtracting a prediction's mean effect over actions cancels whatever the actions share--the action-independent variation where distractors live--leaving a clean, controllable channel, with no reward, no reconstruction, and no distractor-specific auxiliary loss. Because this is only a subtraction at readout time, it applies unchanged to any action-conditioned world model, including frozen pretrained ones. Across a gridworld, synthetic generators with known factors, distracting continuous control, and natural-pixel Atari, the isolated channel recovers the agent's own effect where entangled predictors fail, with nuisance leak indistinguishable from zero; applied post hoc it surfaces an action channel in off-the-shelf models that their raw readouts miss, and it converts into goal-reaching control in the gridworld. We prove the cancellation is exact in finite samples for both discrete and sampled action sets, and we state its measured boundary--distractors whose motion tracks the action--together with the remaining limitations in the appendix.