Prioritized Rollouts for Efficient World Model-based Vision-Language-Action Policy Optimization introduces U‑GROW, a lightweight sampling layer that directs more model rollouts toward states with high policy uncertainty, identified as decision‑sensitive stages where small action differences can alter task outcomes. By modifying only the branched‑start distribution, U‑GROW can be integrated into existing model‑based reinforcement learning pipelines without changing the policy optimization objective. Experiments on simulated and real‑world manipulation tasks demonstrate that U‑GROW improves the efficiency and effectiveness of policy optimization for Vision‑Language‑Action models.
By Yifei Sheng, Haoxiang Ren, Zhilong Zhang, Haonan Wang, Runjie Xu, Yihao Sun, Nan Tang, Zhichao Wu, Lei Yuan, Haoxin Lin, Yang Yu
arXiv:2510. 14828v3 Announce Type: replace Abstract: Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully.
By Jinrui Liu, Bingyan Nie, Boyu Li, Yaran Chen, Yuze Wang, Shunsen He, Haoran Li
arXiv:2606. 15654v1 Announce Type: cross Abstract: Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Observable Markov Decision Process (POMDP) models for real robotics domains remains difficult and labor-intensive.
By Wenjing Tang, Xuanjin Jin, Yuan Liu, Renming Huang, Cewu Lu, Panpan Cai
The paper introduces Predictive Action Chunk Learning (PACL), a method for improving robot manipulation policies using mixed-quality deployment experience. PACL first trains a predictive chunk-level critic to evaluate temporally extended action sequences, then uses the critic’s quality estimates to guide a diffusion actor that learns from both successful and failed rollouts. Experiments on simulated and real robots demonstrate that PACL consistently enhances pretrained policies and outperforms strong imitation learning and offline reinforcement learning baselines.
By Yangang Ren, Yujie Yan, Zirui Li, Jiaming Guo, Di Zeng, Ji Tao, Lan Yu, Xuesong Tian, Chen Lv
arXiv:2508. 08983v2 Announce Type: replace-cross Abstract: Humans can learn a new manipulation task from one or two demonstrations and then perform it in a new room, with new objects, under new constraints.
By Ben Zandonati, Tom\'as Lozano-P\'erez, Leslie Pack Kaelbling
arXiv:2606. 16480v1 Announce Type: cross Abstract: Robots deployed in the real world must plan motions across diverse scenarios without per-scenario retuning.
By Youngjae Min, Jovin D'sa, Faizan M. Tariq, David Isele, Navid Azizan, Sangjae Bae
arXiv:2607. 10706v1 Announce Type: cross Abstract: The action space poses a major challenge in robot learning, since it is often high-dimensional, can span long time horizons, and frequently admits multi-modal optimal solutions.
By Haojie Huang, Zhang Ye, Linfeng Zhao, Boce Hu, Mingxi Jia, Yu Qi, Ahmed Agha, Dian Wang, Robert Platt, Robin Walters
The paper investigates Joint-Embedding Predictive World Models (JEPA-WMs), a class of methods that perform planning in a learned representation space rather than raw input space. It systematically studies how model architecture, training objectives, and planning algorithms influence success across simulated and real‑world robotic tasks, and proposes a JEPA-WM variant that surpasses established baselines in navigation and manipulation. The authors provide code, data, and checkpoints for reproducibility.
By Basile Terver, Tsung-Yen Yang, Jean Ponce, Adrien Bardes, Yann LeCun
The paper introduces STEP, a State‑Aware Task Estimator and Planner that uses multi‑modal large language models to explicitly estimate system states and predict state transitions during task planning. By forecasting future states alongside actions, STEP reduces hallucinated actions and improves task‑convergent planning. In a simulated robot assembly task, STEP outperforms the state‑of‑the‑art by 32.8% in action executability and 14.8% in final‑state error.
By Maitrey Gramopadhye, Prakash Baskaran, Xiao Liu, Songpo Li, Soshi Iba
arXiv:2505. 03296v2 Announce Type: replace-cross Abstract: We present Mixture of Discrete-time Gaussian Processes (MiDiGap), a novel approach for flexible policy representation and imitation learning in robot manipulation.
By Jan Ole von Hartz, Adrian R\"ofer, Joschka Boedecker, Abhinav Valada
arXiv:2608. 11363v1 Announce Type: cross Abstract: A central goal in robot learning is to move beyond task-specific human data collection toward robots that improve through autonomous interaction.
By Shreyas Kowshik, Sreyas Venkataraman, Leo Wang, Niharika Pant, Max Simchowitz, Aviral Kumar
The paper introduces QWM, a framework that integrates world models with standard Q‑learning to perform test‑time search over imagined trajectories. By training the policy and value function solely on real transitions, QWM avoids compounding model bias while still benefiting from predictive search. Experiments on the Robomimic and LIBERO manipulation benchmarks show that QWM outperforms strong prior state‑of‑the‑art methods in both sample efficiency and performance.
By Perry Dong, Yueru Jia, Chelsea Finn, Dorsa Sadigh