# Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models

arXiv: https://arxiv.org/abs/2604.25416 · HTML: https://mlsanity.com/paper/2604.25416/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 42 of its 54 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 30 of 42)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [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)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [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)
- [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)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion](https://mlsanity.com/paper/1807.01675/) (2018)
- [TransDreamer: Reinforcement Learning with Transformer World Models](https://mlsanity.com/paper/2202.09481/) (2022)
- [BYOL-Explore: Exploration by Bootstrapped Prediction](https://mlsanity.com/paper/2206.08332/) (2022)
- [On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract means](https://mlsanity.com/paper/1904.04017/) (2019)
- [Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis](https://mlsanity.com/paper/2502.00935/) (2025)
- [Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures](https://mlsanity.com/paper/2505.00779/) (2025)
- [Optimistic Active Exploration of Dynamical Systems](https://mlsanity.com/paper/2306.12371/) (2023)
- [Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation](https://mlsanity.com/paper/2206.11403/) (2022)
- [Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate](https://mlsanity.com/paper/2210.07553/) (2022)

## Built on by (most cited first, 5 of 5)

- [The Intervention Gap in Latent World Models](https://mlsanity.com/paper/2608.29998/) (2026)
- [Reading the Room: Implicit Confusion Encoding in Recurrent World Model States](https://mlsanity.com/paper/2608.21582/) (2026)
- [DreamLedger: Where to Refuse World-Model Imagination Using Execution-Settled Credit](https://mlsanity.com/paper/2608.23863/) (2026)
- [When World Models Lie: Adaptive Safety Analysis Under Wrong Imaginations](https://mlsanity.com/paper/2609.34300/) (2026)
- [Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust](https://mlsanity.com/paper/2609.37156/) (2026)

## Abstract (arXiv)

Model-based reinforcement learning distinguishes between dynamics models operating on proprioceptive states and latent dynamics models typically operating on high-dimensional image observations. Among the latter, Dreamer's Recurrent State Space Model (RSSM) has emerged as a dominant architecture. While ensemble-based epistemic uncertainty has proven effective in proprioceptive dynamics for mitigating model exploitation, guiding exploration, or promoting caution, its behavior in latent dynamics remains largely unexplored. Our experiments reveal that although ensemble disagreement captures local epistemic uncertainty, it does not reliably reflect global compounding model error accumulated over prolonged RSSM latent rollouts. We provide evidence for an attractor behavior that draws rollouts toward well-supported latent regions, where uncertainty diminishes despite increasing discrepancies from the true environment dynamics. This can cause the model to overestimate returns when attractor regions correspond to high-reward behaviors. Our findings reveal a structural limitation of epistemic uncertainty estimation in RSSMs and challenge the assumption that epistemic uncertainty estimation transfers directly from proprioceptive to latent dynamics.