PRISM：面向3D视觉-语言基于偏好的强化学习的隐式场景建模偏好精炼方法
PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning
AI总结：
本研究提出PRISM框架，融合3D点云-语言模型与思维链推理，解决2D基于偏好强化学习的遮挡、视角偏差及短视问题，提升偏好一致率、收敛速度与泛化性，支撑可扩展的人类对齐强化学习。
摘要：
我们提出PRISM这一新型框架，旨在通过统一3D点云建模与具备未来感知能力的偏好精炼，克服基于2D的基于偏好的强化学习（Preference-Based Reinforcement Learning, PBRL）的局限性。PRISM的核心采用3D点云-语言模型（3D Point Cloud-Language Model, 3D-PC-LLM），以缓解遮挡与视角偏差，确保偏好信号更稳定且具备空间一致性。此外，PRISM利用思维链（Chain-of-Thought, CoT）推理纳入长程考量，从而避免静态偏好比较中常见的短视反馈。与传统PBRL技术相比，这种3D感知与未来导向推理的融合大幅提升了偏好一致率，加快了策略收敛速度，并在未见过的机器人环境中具备强泛化性。我们的实证结果覆盖机器人操作与自主导航等任务，凸显了PRISM在精准空间理解与可靠长期决策至关重要的现实场景中的应用潜力。通过将3D几何感知与CoT驱动的偏好建模相结合，PRISM为可扩展、符合人类意图的强化学习奠定了全面基础。
英文摘要：
We propose PRISM, a novel framework designed to overcome the limitations of 2D-based Preference-Based Reinforcement Learning (PBRL) by unifying 3D point cloud modeling and future-aware preference refinement. At its core, PRISM adopts a 3D Point Cloud-Language Model (3D-PC-LLM) to mitigate occlusion and viewpoint biases, ensuring more stable and spatially consistent preference signals. Additionally, PRISM leverages Chain-of-Thought (CoT) reasoning to incorporate long-horizon considerations, thereby preventing the short-sighted feedback often seen in static preference comparisons. In contrast to conventional PBRL techniques, this integration of 3D perception and future-oriented reasoning leads to significant gains in preference agreement rates, faster policy convergence, and robust generalization across unseen robotic environments. Our empirical results, spanning tasks such as robotic manipulation and autonomous navigation, highlight PRISM's potential for real-world applications where precise spatial understanding and reliable long-term decision-making are critical. By bridging 3D geometric awareness with CoT-driven preference modeling, PRISM establishes a comprehensive foundation for scalable, human-aligned reinforcement learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
