# WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT

arXiv: https://arxiv.org/abs/2606.17906 · HTML: https://mlsanity.com/paper/2606.17906/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 20 of its 20 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Placed in

- World models / [Latent dynamics models and model-based RL](https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/)
- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 20 of 20)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning](https://mlsanity.com/paper/2509.09674/) (2025)
- [Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation](https://mlsanity.com/paper/2508.05635/) (2025)
- [Interactive Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2505.17016/) (2025)
- [Self-Improving Vision-Language-Action Models with Data Generation via Residual RL](https://mlsanity.com/paper/2511.00091/) (2025)
- [VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators](https://mlsanity.com/paper/2510.00406/) (2025)
- [GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2512.01801/) (2025)
- [CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning](https://mlsanity.com/paper/2508.02219/) (2025)
- [π_textttRL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models](https://mlsanity.com/paper/2510.25889/) (2025)
- [Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models](https://mlsanity.com/paper/2509.04063/) (2025)
- [TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation](https://mlsanity.com/paper/2602.09023/) (2026)

## Built on by (most cited first, 4 of 4)

- [WAM-OPD: On-Policy Distillation for World Action Models](https://mlsanity.com/paper/2608.22364/) (2026)
- [WAM-OPD: Sharpening World Action Models via On-Policy Distillation](https://mlsanity.com/paper/2609.34250/) (2026)
- [Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation](https://mlsanity.com/paper/2609.37398/) (2026)
- [PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning](https://mlsanity.com/paper/2609.38890/) (2026)

## Abstract (arXiv)

Recent World-Action (WA) models demonstrate strong generalization ability and data efficiency, but they typically rely on expert trajectories for training. This reliance limits their ability to acquire fine-grained manipulation skills beyond the demonstration distribution and prevents them from continuously improving through real-world interaction. To address these limitations, we propose WAM-RL, a reinforcement learning framework that enables joint optimization of the world model and the action model through online interaction with the environment. By allowing the two components to co-evolve, our approach enhances fine-grained control and adaptability. Specifically, a WA model consists of a world model and an actor. We design a tailored reinforcement learning method with hierarchical optimization to coordinate their improvement. On the methodological side, we systematically investigate the effects of applying reinforcement learning to the action model, as well as online training of the world model within an RL setting. Our experiments reveal a key insight: optimizing only the actor yields improvements on short-horizon tasks, but fails to provide significant gains on long-horizon tasks. In contrast, jointly optimizing both the world model and the actor is critical for achieving strong performance in long-horizon settings. Our work is the first to introduce reinforcement learning into the World-Action paradigm, and provides insights into how online optimization of both the action head and the world model impacts overall performance.