PulseAugur
实时 16:03:28
English(EN) Distributionally Robust and Safe Imitation Learning

新框架增强模仿学习的安全性与鲁棒性

研究人员开发了一个新的模仿学习(IL)框架,增强了其在分布变化下的安全性和鲁棒性。该方法结合了泰勒级数模仿学习(TaSIL)来解决策略引起的偏移,以及分布鲁棒自适应控制来处理不确定性引起的偏移。该统一框架在遵守安全约束的同时,优化了在分布不确定性下的性能,这在一个无人机在不确定环境中导航的案例研究中得到了证明。 AI

影响 该框架可以提高在不可预测环境中运行的自主系统的安全性和可靠性。

排序理由 该集群包含一篇在arXiv上发表的研究论文,详细介绍了一个新的模仿学习框架。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新框架增强模仿学习的安全性与鲁棒性

报道来源 [3]

  1. arXiv cs.LG TIER_1 English(EN) · Somjit Nath, Abdelhak Lemkhenter, Pallavi Choudhury, Chris Lovett, Katja Hofmann, Sergio Valcarcel Macua, Lukas Sch\"afer ·

    流式视频游戏鲁棒高效模仿学习的增强方法

    arXiv:2607.14200v1 Announce Type: new Abstract: Imitation learning is an appealing way to scale game-playing agents to complex 3D environments by training policies to map visual observations to actions from human demonstrations. However, these demonstrations are expensive to coll…

  2. arXiv cs.LG TIER_1 English(EN) · Ahmed Aboudonia, Naira Hovakimyan ·

    分布鲁棒且安全的模仿学习

    arXiv:2607.13436v1 Announce Type: new Abstract: Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally ro…

  3. arXiv cs.LG TIER_1 English(EN) · Naira Hovakimyan ·

    分布鲁棒且安全的模仿学习

    Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addre…