SHORE (Stability‑Hybrid On‑Policy Reinforcement Learning) tackles online 3D bin packing by jointly deciding which box to pack, its orientation, and placement while ensuring stack stability. It learns a stability probability via a 3D U‑Net from both executed outcomes and simulated alternatives, and incorporates these predictions into a discrete on‑policy actor‑critic that gates the influence of an untrained model. In Isaac Gym experiments, SHORE achieves 73 % space utilization in 0.4 M steps—twice as fast as a baseline without stability modeling—and outperforms the GOPT baseline on a 60‑box set, albeit with a slightly higher placement‑failure rate.
whyItMatters":"The method demonstrates that integrating learned stability predictions into reinforcement learning accelerates learning and improves packing efficiency in realistic, high‑risk bin‑packing scenarios."
By Chang Shi, Ann Majewicz Fey
arXiv:2609.13234v1 Announce Type: cross
Abstract: Industrialized construction imposes stringent precision requirements on robotic assembly of modular components such as prefabricated window units. In...
By Zekai Jin, Huiguang Wang, Xiaoning Sun, Yi Shao
arXiv:2607. 09866v1 Announce Type: cross Abstract: Offline-to-online reinforcement learning is promising for generalizable robotic manipulation, yet its full-stack complexity obscures reproduction and diagnosis.
By Wenke Xia, Pei Ren, Wenbo Yu, Yizhuo Zhang, Jifan Li, Yixue Zhang, Yinuo Zhao, Qingyang Gao, Jianlong Fu, Jian Tang, Ji-Rong Wen, Zhengping Che, Di Hu
The paper introduces RBGA, an algorithm for offline-to-online safe reinforcement learning in dexterous manipulation. RBGA tracks the remaining safety budget during an episode and uses it to arbitrate between offline guidance and an evolving online policy, comparing cost-to-go estimates at each step. The authors provide theoretical analysis of safety implications and demonstrate through experiments that RBGA improves online policy performance while preserving safety.
By Zongyou Yu, Ao Zhou, Xiongbo Shi, Jiayi Guan, Shihang Du, Xudong Zhang, Shangding Gu, Junqiao Zhao, Hanli Wang, Guang Chen
arXiv:2608. 15680v1 Announce Type: cross Abstract: Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states.
By Yijie Xu, Haopeng Jin, Run Zhou, Shengbang Liu, Sixiang Chen, Hongyang Cheng, Sicheng Hu, Peterson Co, Jinwen Luo, Huajie Tan, Shanghang Zhang
Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as fo...
arXiv:2607. 21302v1 Announce Type: new Abstract: Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations.
By Gong Gao, Weidong Zhao, Xianhui Liu, Ning Jia
arXiv:2606. 31377v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon robotic manipulation is often limited by sparse and delayed rewards, while manually designing dense shaping signals is costly and brittle to changes in environments and object configurations.
By Yang Yang, Bingjie Chen, Zihan Wang, Yizhe Li, Guoping Pan, Yi Cheng, Houde Liu
arXiv:2602. 13977v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots.
By Zhennan Jiang, Shangqing Zhou, Yutong Jiang, Zefang Huang, Mingjie Wei, Yuhui Chen, Tianxing Zhou, Zhen Guo, Hao Lin, Quanlu Zhang, Yu Wang, Haoran Li, Chao Yu, Dongbin Zhao
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
The paper introduces Rollback, a method that uses action‑conditioned world models to backtrack to critical decision points, branch into alternative actions, and compare outcomes to attribute success to individual decisions. By turning world models into counterfactual engines, Rollback provides fine‑grained, action‑level supervision without a separate value model and integrates distributed world‑model search with asynchronous real‑robot execution. Experiments on block extraction, ball tossing, and tabletop curling show that Rollback improves success rates by over 10% compared to the strongest baseline and surpasses human performance on two tasks within eight hours of training.
By Jiayi Luo, Yang Zhang, Liliang Chen, Nan Wang, Chen Gao, Boxiang Qiu, Zhuoxuan Li, Baorui Peng, Chuankang Li, Yuxiang Yan, Si Liu, Qingyun Sun, Shuicheng Yan, Maoqing Yao, Jianxin Li, Guanghui Ren
arXiv:2605. 05172v2 Announce Type: replace-cross Abstract: Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning.
By Lakshita Dodeja, Ondrej Biza, Shivam Vats, Stephen Hart, Stefanie Tellex, Robin Walters, Karl Schmeckpeper, Thomas Weng