# Simplifying Latent Dynamics with Softly State-Invariant World Models

arXiv: https://arxiv.org/abs/2401.17835 · HTML: https://mlsanity.com/paper/2401.17835/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 34 of its 53 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [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)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [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)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [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)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model](https://mlsanity.com/paper/1907.00953/) (2019)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [DARLA: Improving Zero-Shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/1707.08475/) (2017)
- [From Variational to Deterministic Autoencoders](https://mlsanity.com/paper/1903.12436/) (2019)
- [Generalization and Regularization in DQN](https://mlsanity.com/paper/1810.00123/) (2018)
- [The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels](https://mlsanity.com/paper/2101.02722/) (2021)
- [InfoBot: Transfer and Exploration via the Information Bottleneck](https://mlsanity.com/paper/1901.10902/) (2019)
- [Denoised MDPs: Learning World Models Better Than the World Itself](https://mlsanity.com/paper/2206.15477/) (2022)
- [Understanding Self-Predictive Learning for Reinforcement Learning](https://mlsanity.com/paper/2212.03319/) (2022)
- [Robust Predictable Control](https://mlsanity.com/paper/2109.03214/) (2021)
- [Dynamic Bottleneck for Robust Self-Supervised Exploration](https://mlsanity.com/paper/2110.10735/) (2021)

## Built on by (most cited first, 10 of 10)

- [MRI Contrast Enhancement Kinetics World Model](https://mlsanity.com/paper/2602.19285/) (2026)
- [Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges](https://mlsanity.com/paper/2603.09086/) (2026)
- [DWM: Separating World Effects from Actions in Latent World Models](https://mlsanity.com/paper/2607.18715/) (2026)
- [ResWM: Residual-Action World Model for Visual RL](https://mlsanity.com/paper/2603.11110/) (2026)
- [World Model-Enabled Causal Digital Twins for Semantic Communications in Physical AI Systems](https://mlsanity.com/paper/2605.16547/) (2026)
- [Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection](https://mlsanity.com/paper/2608.06706/) (2026)
- [A circuit for predicting hierarchical structure in-context in Large Language Models](https://mlsanity.com/paper/2509.21534/) (2025)
- [Learning Permutation-invariant Macroscopic Dynamics](https://mlsanity.com/paper/2605.30812/) (2026)
- [Prediction horizon shapes representations in predictive learning](https://mlsanity.com/paper/2511.09290/) (2025)
- [World Models in Pieces: Structural Certification for General Agents](https://mlsanity.com/paper/2606.24842/) (2026)

## Abstract (arXiv)

To solve control problems via model-based reasoning or planning, an agent needs to know how its actions affect the state of the world. The actions an agent has at its disposal often change the state of the environment in systematic ways. However, existing techniques for world modelling do not guarantee that the effect of actions are represented in such systematic ways. We introduce the Parsimonious Latent Space Model (PLSM), a world model that regularizes the latent dynamics to make the effect of the agent's actions more predictable. Our approach minimizes the mutual information between latent states and the change that an action produces in the agent's latent state, in turn minimizing the dependence the state has on the dynamics. This makes the world model softly state-invariant. We combine PLSM with different model classes used for i) future latent state prediction, ii) planning, and iii) model-free reinforcement learning. We find that our regularization improves accuracy, generalization, and performance in downstream tasks, highlighting the importance of systematic treatment of actions in world models.