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."
Online 3D bin packing with a processing buffer requires choosing which box to pack, its orientation, and its placement while keeping the stack stable under unknown future arrivals. A collapse ends the...
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...
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.
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.
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.
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.
arXiv:2607. 09773v1 Announce Type: new Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments.
arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.
arXiv:2610.07613v1 Announce Type: cross Abstract: In mill yards, log loaders clear dense piles by a sequence of bundle grasps: hundreds of logs rest in contact, and each removal changes the pile avai...
arXiv:2607. 14171v1 Announce Type: new Abstract: Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes.
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.
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.