Generalizable visual reinforcement learning with segment anything model

Z Yuan, T Wei, S Cheng, G Zhang, Y Chen… - arXiv preprint arXiv …, 2024 - arxiv.org

Can we endow visuomotor robots with generalization capabilities to operate in diverse open-
world scenarios? In this paper, we propose\textbf {Maniwhere}, a generalizable framework …

被引用次数：7 相关文章所有 4 个版本

[PDF] arxiv.org

Point-SAM: Promptable 3D Segmentation Model for Point Clouds

Y Zhou, J Gu, TY Chiang, F Xiang, H Su - arXiv preprint arXiv:2406.17741, 2024 - arxiv.org

The development of 2D foundation models for image segmentation has been significantly
advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D …

被引用次数：1 相关文章所有 2 个版本

[PDF] arxiv.org

SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation

J Zhang, C Bai, H He, W Xia, Z Wang, B Zhao… - arXiv preprint arXiv …, 2024 - arxiv.org

Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of
scene understanding and action prediction. Current methods employ both 3D representation …

被引用次数：5 相关文章所有 3 个版本

[PDF] arxiv.org

Policy-shaped prediction: avoiding distractions in model-based reinforcement learning

M Hutson, I Kauvar, N Haber - arXiv preprint arXiv:2412.05766, 2024 - arxiv.org

Model-based reinforcement learning (MBRL) is a promising route to sample-efficient policy
optimization. However, a known vulnerability of reconstruction-based MBRL consists of …

Focus On What Matters: Separated Models For Visual-Based RL Generalization

D Zhang, B Lv, H Zhang, F Yang, J Zhao, H Yu… - arXiv preprint arXiv …, 2024 - arxiv.org

A primary challenge for visual-based Reinforcement Learning (RL) is to generalize
effectively across unseen environments. Although previous studies have explored different …