# ResWM: Residual-Action World Model for Visual RL

arXiv: https://arxiv.org/abs/2603.11110 · HTML: https://mlsanity.com/paper/2603.11110/

## 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 32 of its 57 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- 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, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://mlsanity.com/paper/2304.01186/) (2023)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [DeepMDP: Learning Continuous Latent Space Models for Representation Learning](https://mlsanity.com/paper/1906.02736/) (2019)
- [Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2406.01900/) (2024)
- [Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation](https://mlsanity.com/paper/2107.00644/) (2021)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning](https://mlsanity.com/paper/2506.05207/) (2025)
- [Manifold Gaussian Processes for Regression](https://mlsanity.com/paper/1402.5876/) (2014)
- [CF-VLM:CounterFactual Vision-Language Fine-tuning](https://mlsanity.com/paper/2506.17267/) (2025)
- [GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning](https://mlsanity.com/paper/2505.23399/) (2025)
- [TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning](https://mlsanity.com/paper/2306.13229/) (2023)
- [Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2509.16630/) (2025)
- [PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning](https://mlsanity.com/paper/2106.04152/) (2021)
- [KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems](https://mlsanity.com/paper/2502.07350/) (2025)
- [MAT-Agent: Adaptive Multi-Agent Training Optimization](https://mlsanity.com/paper/2510.17845/) (2025)
- [DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off](https://mlsanity.com/paper/2509.02785/) (2025)
- [MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models](https://mlsanity.com/paper/2512.08228/) (2025)
- [ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment](https://mlsanity.com/paper/2509.17818/) (2025)
- [A Survey on Physics Informed Reinforcement Learning: Review and Open Problems](https://mlsanity.com/paper/2309.01909/) (2023)
- [Reinforcement Learning with Latent Flow](https://mlsanity.com/paper/2101.01857/) (2021)
- [Top-Down Semantic Refinement for Image Captioning](https://mlsanity.com/paper/2510.22391/) (2025)

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

- [LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving](https://mlsanity.com/paper/2607.11964/) (2026)
- [AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites](https://mlsanity.com/paper/2605.06841/) (2026)

## Abstract (arXiv)

Learning predictive world models from raw visual observations is a central challenge in reinforcement learning (RL), especially for robotics and continuous control. Conventional model-based RL frameworks directly condition future predictions on absolute actions, which makes optimization unstable: the optimal action distributions are task-dependent, unknown a priori, and often lead to oscillatory or inefficient control. To address this, we introduce the Residual-Action World Model (ResWM), a new framework that reformulates the control variable from absolute actions to residual actions -- incremental adjustments relative to the previous step. This design aligns with the inherent smoothness of real-world control, reduces the effective search space, and stabilizes long-horizon planning. To further strengthen the representation, we propose an Observation Difference Encoder that explicitly models the changes between adjacent frames, yielding compact latent dynamics that are naturally coupled with residual actions. ResWM is integrated into a Dreamer-style latent dynamics model with minimal modifications and no extra hyperparameters. Both imagination rollouts and policy optimization are conducted in the residual-action space, enabling smoother exploration, lower control variance, and more reliable planning. Empirical results on the DeepMind Control Suite demonstrate that ResWM achieves consistent improvements in sample efficiency, asymptotic returns, and control smoothness, significantly surpassing strong baselines such as Dreamer and TD-MPC. Beyond performance, ResWM produces more stable and energy-efficient action trajectories, a property critical for robotic systems deployed in real-world environments. These findings suggest that residual action modeling provides a simple yet powerful principle for bridging algorithmic advances in RL with the practical requirements of robotics.