The paper introduces the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning into distinct latent spaces and dynamics models. A new learning method, Long-Horizon Representation Learning with Weighted Rollout (LoRe), supervises predictions at both levels using exponential horizon weights. Experiments on five goal-conditioned visual control tasks show that Dual-WM improves success rates over strong baselines, especially at longer horizons.
By Delin Zhao, Zhengrong Yue, Shaobin Zhuang, Junlin He, Xiaoyu Chen, Zikang Wang, Yuxin Liu, Limin Wang, Yali Wang
arXiv:2608.24855v1 Announce Type: new
Abstract: Latent world models are inherently strong encoders that transform image pixel to latent embedding, yet existing world models still rely on online traje...
By Hsiang-Wei Huang, Jianxu Shangguan, Junbin Lu, Jenq-Neng Hwang
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
By Wancong Zhang, Basile Terver, Artem Zholus, Soham Chitnis, Harsh Sutaria, Mido Assran, Randall Balestriero, Amir Bar, Adrien Bardes, Yann LeCun, Nicolas Ballas
The paper introduces Dwell, a model‑based reinforcement learning framework that treats a pretrained vision‑language model (VLM) as a recurrent latent transition operator. Dwell enables the VLM to predict, adjust, and act within its own latent space, allowing the agent to learn from real interactions and latent imagination without reconstructing full futures. Experiments across five interactive visual environments show that Dwell outperforms other trainable methods while significantly reducing computational demands for imagination.
By Haoxi Li, Sikai Bai, Jianfei Ma, Qinglin Hou, Xiaocheng Lu, Tao Han, Jie Zhang, Song Guo
The paper introduces DRILL, a bilevel training framework that optimizes world models for policy improvement rather than pixel accuracy. DRILL-VWI reweights prediction errors using policy visitation and model confidence, while DRILL-IMG employs meta‑gradients to directly maximize downstream policy returns. Experiments on manipulation simulators show DRILL-IMG boosts success rates by 13.1 points over WMPO and 7.9 points over RLVR-World, demonstrating that world models can be more effectively trained using policy gradients.
Contrastive World Models propose a new method for learning latent dynamics without pixel reconstruction. By replacing observation reconstruction with a Deep InfoMax-like objective that maximizes mutual information between state-action sequences and local patch features of future observations, the approach encourages state representations to retain predictive information while ignoring visually irrelevant details. Experiments show that this method matches existing baselines in simple settings and significantly outperforms them when distractors or natural video backgrounds are present, while also training more efficiently by eliminating the pixel decoder.
By Bonnie Li
Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction).
arXiv:2607. 20834v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets.
By Ahad Jawaid
arXiv:2608. 05989v1 Announce Type: new Abstract: Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL).
By Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen
arXiv:2610.27280v1 Announce Type: cross
Abstract: Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based meth...
By Yunzhe Hu, Dong Xu
PAVXploreRL introduces a reinforcement learning framework that builds on a pretrained latent world model to explicitly optimize Physical Plausibility, Action Adherence, and Visual Fidelity (PAV) objectives. By combining in‑distribution expert trajectories with noise‑driven out‑of‑distribution action exploration, the method avoids reliance on paired video supervision and improves generalization. Experiments demonstrate a 5.6% average performance gain over pretrained baselines and more reliable policy evaluation with reduced overestimation bias.
By Han Wang, Zijun Wang, Shuoshuo Xue, Rui Cao, Fengjiao Chen, Xiaodan Liang, Roy Ka-Wei Lee
arXiv:2606.20627v2 Announce Type: replace
Abstract: Joint-Embedding Predictive Architectures (JEPAs) enable agents to plan in latent space by imagining the outcomes of candidate actions, yet task spe...
By Samuel Barbeau, Simon Roy, Giovanni Beltrame, Christian Desrosiers, Nicolas Thome