# Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning

arXiv: https://arxiv.org/abs/2504.07095 · HTML: https://mlsanity.com/paper/2504.07095/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [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)
- [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)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics](https://mlsanity.com/paper/2005.04269/) (2020)
- [Dissecting Neural ODEs](https://mlsanity.com/paper/2002.08071/) (2020)
- [Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints](https://mlsanity.com/paper/2010.13581/) (2020)
- [ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics](https://mlsanity.com/paper/1810.01054/) (2018)
- [NeuralSim: Augmenting Differentiable Simulators with Neural Networks](https://mlsanity.com/paper/2011.04217/) (2020)
- [On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning](https://mlsanity.com/paper/2210.10763/) (2022)
- [Simple Emergent Action Representations from Multi-Task Policy Training](https://mlsanity.com/paper/2210.09566/) (2022)

## Built on by (most cited first, 11 of 11)

- [A Survey: Learning Embodied Intelligence from Physical Simulators and World Models](https://mlsanity.com/paper/2507.00917/) (2025)
- [Do World Action Models Generalize Better than VLAs? A Robustness Study](https://mlsanity.com/paper/2603.22078/) (2026)
- [A Mechanistic View on Video Generation as World Models: State and Dynamics](https://mlsanity.com/paper/2601.17067/) (2026)
- [Overcoming Statistical Bias in Action-Controllable World Models](https://mlsanity.com/paper/2608.04653/) (2026)
- [Constrained Decoding for Safe Robot Navigation Foundation Models](https://mlsanity.com/paper/2509.01728/) (2025)
- [SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments](https://mlsanity.com/paper/2511.23465/) (2025)
- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models](https://mlsanity.com/paper/2510.26782/) (2025)
- [Alpha-RF: Automated RF-Filter-Circuit Design with Neural Simulator and Reinforcement Learning](https://mlsanity.com/paper/2603.00104/) (2026)
- [MotionPyramid: Hierarchical Motion Representation and Residual Interfaces](https://mlsanity.com/paper/2606.20705/) (2026)
- [Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies](https://mlsanity.com/paper/2609.28670/) (2026)

## Abstract (arXiv)

An embodied system must not only model the patterns of the external world but also understand its own motion dynamics. A motion dynamic model is essential for efficient skill acquisition and effective planning. In this work, we introduce the neural motion simulator (MoSim), a world model that predicts the future physical state of an embodied system based on current observations and actions. MoSim achieves state-of-the-art performance in physical state prediction and provides competitive performance across a range of downstream tasks. This works shows that when a world model is accurate enough and performs precise long-horizon predictions, it can facilitate efficient skill acquisition in imagined worlds and even enable zero-shot reinforcement learning. Furthermore, MoSim can transform any model-free reinforcement learning (RL) algorithm into a model-based approach, effectively decoupling physical environment modeling from RL algorithm development. This separation allows for independent advancements in RL algorithms and world modeling, significantly improving sample efficiency and enhancing generalization capabilities. Our findings highlight that world models for motion dynamics is a promising direction for developing more versatile and capable embodied systems.