强化学习的许多应用都可以正式化为目标条件的环境,在每个情节中,都有一个“目标”会影响该情节中获得的奖励,但不会影响动态。已经提出了各种技术来提高目标条件环境的性能,例如自动课程生成和目标重新标记。在这项工作中,我们探讨了在目标条件设置中的损失钢筋学习与知识蒸馏之间的联系。特别是:当前的Q值函数和目标Q值估计是该目标的函数,我们想训练Q值函数以匹配其所有目标的目标。因此,我们将基于梯度的注意转移(Zagoruyko和Komodakis 2017)(一种知识蒸馏技术)应用于Q功能更新。我们从经验上表明,当目标空间高维时,这可以提高目标条件的非政策强化学习的性能。我们还表明,在多个同时稀疏目标的情况下,可以对该技术进行调整,以允许有效学习,在这种情况下,代理可以通过在测试时间指定的所有大型目标来实现奖励。最后,为了提供理论支持,我们给出了环境类别的示例,在某些假设下(在某些假设)中,标准的非政策算法至少需要O(d^2)观察到的过渡以学习最佳策略,而我们的建议技术仅需O( d)过渡,其中d是目标和状态空间的维度。
translated by 谷歌翻译
数据中毒考虑了一个对手,该对手扭曲了用于恶意目的的机器学习算法的训练集。在这项工作中,我们揭示了一个关于数据中毒基本原理的猜想,我们称之为致命的剂量猜想。猜想指出:如果需要$ n $清洁的训练样品才能进行准确的预测,则在尺寸 - $ n $训练套件中,只能在确保准确性的同时耐受$ \ theta(n/n)$中毒样品。从理论上讲,我们在多种情况下验证了这一猜想。我们还通过分配歧视提供了对这种猜想的更普遍的看法。深度分区聚合(DPA)及其扩展,有限聚合(FA)是可证明防御数据中毒的可证明防御方法的方法,他们通过使用给定的学习者从不同的培训集中训练的许多基本模型对许多基本模型进行了预测。猜想意味着DPA和FA都是最佳的 - 如果我们拥有最高的学习者,它们可以将其变成针对数据中毒的最强大的防御能力之一。这概述了一种实用方法,可以通过寻找数据效率的学习者来开发更强大的防御能力。从经验上讲,作为概念的证明,我们表明,通过简单地为基础学习者使用不同的数据增强,我们可以分别将DPA在CIFAR-10和GTSRB上的认证稳健性和三倍,而无需牺牲准确性。
translated by 谷歌翻译
大型语言模型可以编码有关世界的大量语义知识。这种知识对于旨在采取自然语言表达的高级,时间扩展的指示的机器人可能非常有用。但是,语言模型的一个重大弱点是,它们缺乏现实世界的经验,这使得很难利用它们在给定的体现中进行决策。例如,要求语言模型描述如何清洁溢出物可能会导致合理的叙述,但是它可能不适用于需要在特定环境中执行此任务的特定代理商(例如机器人)。我们建议通过预处理的技能来提供现实世界的基础,这些技能用于限制模型以提出可行且在上下文上适当的自然语言动作。机器人可以充当语​​言模型的“手和眼睛”,而语言模型可以提供有关任务的高级语义知识。我们展示了如何将低级技能与大语言模型结合在一起,以便语言模型提供有关执行复杂和时间扩展说明的过程的高级知识,而与这些技能相关的价值功能则提供了连接必要的基础了解特定的物理环境。我们在许多现实世界的机器人任务上评估了我们的方法,我们表明了对现实世界接地的需求,并且这种方法能够在移动操纵器上完成长远,抽象的自然语言指令。该项目的网站和视频可以在https://say-can.github.io/上找到。
translated by 谷歌翻译
数据中毒攻击旨在通过扭曲培训数据来操纵模型行为。以前,提出了基于聚合的认证辩护,深度分区聚合(DPA),以减轻这种威胁。 DPA通过在数据不相交子集对基础分类器的聚合中进行预测,从而限制了其对数据集畸变的敏感性。在这项工作中,我们提出了对一般中毒攻击的经过改进的辩护,即有限的聚集。与直接将训练设置为不相交子集的DPA相反,我们的方法首先将训练设置分为较小的不相交子集,然后将它们的重复项组合在一起,以构建较大(但不是不相关的)子集来用于培训基础分类器。这减少了毒药样品的最严重影响,从而改善了认证的鲁棒性界限。此外,我们还提供了我们方法的替代视图,桥接了确定性和基于随机聚合的认证防御的设计。从经验上讲,我们提出的有限聚合一致地改善了MNIST,CIFAR-10和GTSRB的证书,将认证的分数提高了高达3.05%,3.87%和4.77%,同时保持与DPA相同的清洁精度,实际上建立了新的状态对数据中毒的(尖锐)认证的鲁棒性。
translated by 谷歌翻译
对象检测在许多安全关键系统中播放关键作用。对抗性补丁攻击,在物理世界中易于实施,对最先进的对象探测器构成严重威胁。开发针对补丁攻击的对象探测器的可靠防御是至关重要的,但严重解读。在本文中,我们提出了段和完整的防御(SAC),是通过检测和消除对抗性补丁来保护对象探测器的一般框架。我们首先培训一个补丁分段器,输出补丁掩码,提供对抗性补丁的像素级定位。然后,我们提出了一种自我逆势训练算法来强制补丁分段器。此外,我们设计了一种坚固的形状完成算法,保证了给定贴片分段器的输出在地面真理贴片掩模的某个汉明距离的图像中从图像中移除整个修补程序。我们对Coco和Xview Datasets的实验表明,即使在具有清洁图像上没有性能下降的强大自适应攻击下,SAC也可以实现优越的稳健性,并且概括到未遵守的补丁形状,攻击预算和看不见的攻击方法。此外,我们介绍了股份模型数据集,该数据集增强了具有对抗修补程序的像素级注释的杏子数据集。我们展示SAC可以显着降低物理补丁攻击的目标攻击成功率。
translated by 谷歌翻译
通过模仿学习(IL)使用用户提供的演示,或者通过使用大量的自主收集的体验来学习机器人技能。方法具有互补的经验和缺点:RL可以达到高度的性能,但需要缺陷,但是需要缺乏要求,但是需要达到高水平的性能,但需要达到高度的性能这可能非常耗时和不安全; IL不要求Xploration,但只学习与所提供的示范一样好的技能。一种方法将两种方法的优势结合在一起?一系列的方法旨在解决这个问题,提出了整合IL和RL的元素的各种技术。然而,扩大了这种方法,这些方法复杂的机器人技能,整合了不同的离线数据,概括到现实世界的情景仍然存在重大挑战。在本文中,USAIM是测试先前IL + RL算法的可扩展性,并设计了一种系统的详细实验实验,这些实验结合了现有的组件,其具有效果有效和可扩展的方式。为此,我们展示了一系列关于了解每个设计决定的影响的一系列实验,以便开发可以利用示范和异构的先前数据在一系列现实世界和现实的模拟问题上获得最佳表现的批准方法。我们通过致电Wap-opt的完整方法将优势加权回归[1,2]和QT-opt [3]结合在一起,提供了一个UnifiedAgveach,用于集成机器人操作的演示和离线数据。请参阅HTTPS: //awopt.github.io有关更多详细信息。
translated by 谷歌翻译
强化学习可以培训有效执行复杂任务的政策。然而,对于长地平线任务,这些方法的性能与地平线脱落,通常需要推理和构成较低级别的技能。等级强化学习旨在通过为行动抽象提供一组低级技能来实现这一点。通过抽象空间状态,层次结构也可以进一步提高这一点。我们对适当的状态抽象应取决于可用的较低级别策略的功能。我们提出了价值函数空间:通过使用与每个较低级别的技能对应的值函数来产生这种表示的简单方法。这些价值函数捕获场景的可取性,从而形成了紧凑型摘要任务相关信息的表示,并强大地忽略了分散的人。迷宫解决和机器人操纵任务的实证评估表明,我们的方法提高了长地平的性能,并且能够比替代的无模型和基于模型的方法能够更好的零拍泛化。
translated by 谷歌翻译
In the past years, deep learning has seen an increase of usage in the domain of histopathological applications. However, while these approaches have shown great potential, in high-risk environments deep learning models need to be able to judge their own uncertainty and be able to reject inputs when there is a significant chance of misclassification. In this work, we conduct a rigorous evaluation of the most commonly used uncertainty and robustness methods for the classification of Whole-Slide-Images under domain shift using the H\&E stained Camelyon17 breast cancer dataset. Although it is known that histopathological data can be subject to strong domain shift and label noise, to our knowledge this is the first work that compares the most common methods for uncertainty estimation under these aspects. In our experiments, we compare Stochastic Variational Inference, Monte-Carlo Dropout, Deep Ensembles, Test-Time Data Augmentation as well as combinations thereof. We observe that ensembles of methods generally lead to higher accuracies and better calibration and that Test-Time Data Augmentation can be a promising alternative when choosing an appropriate set of augmentations. Across methods, a rejection of the most uncertain tiles leads to a significant increase in classification accuracy on both in-distribution as well as out-of-distribution data. Furthermore, we conduct experiments comparing these methods under varying conditions of label noise. We observe that the border regions of the Camelyon17 dataset are subject to label noise and evaluate the robustness of the included methods against different noise levels. Lastly, we publish our code framework to facilitate further research on uncertainty estimation on histopathological data.
translated by 谷歌翻译
Charisma is considered as one's ability to attract and potentially also influence others. Clearly, there can be considerable interest from an artificial intelligence's (AI) perspective to provide it with such skill. Beyond, a plethora of use cases opens up for computational measurement of human charisma, such as for tutoring humans in the acquisition of charisma, mediating human-to-human conversation, or identifying charismatic individuals in big social data. A number of models exist that base charisma on various dimensions, often following the idea that charisma is given if someone could and would help others. Examples include influence (could help) and affability (would help) in scientific studies or power (could help), presence, and warmth (both would help) as a popular concept. Modelling high levels in these dimensions for humanoid robots or virtual agents, seems accomplishable. Beyond, also automatic measurement appears quite feasible with the recent advances in the related fields of Affective Computing and Social Signal Processing. Here, we, thereforem present a blueprint for building machines that can appear charismatic, but also analyse the charisma of others. To this end, we first provide the psychological perspective including different models of charisma and behavioural cues of it. We then switch to conversational charisma in spoken language as an exemplary modality that is essential for human-human and human-computer conversations. The computational perspective then deals with the recognition and generation of charismatic behaviour by AI. This includes an overview of the state of play in the field and the aforementioned blueprint. We then name exemplary use cases of computational charismatic skills before switching to ethical aspects and concluding this overview and perspective on building charisma-enabled AI.
translated by 谷歌翻译
Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton formats provided by different datasets, i.e., they do not label the same set of anatomical landmarks. There is little prior research on how to best supervise one model with such discrepant labels. We show that simply using separate output heads for different skeletons results in inconsistent depth estimates and insufficient information sharing across skeletons. As a remedy, we propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. The discovered latent 3D points capture the redundancy among skeletons, enabling enhanced information sharing when used for consistency regularization. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset. Our code and models are available for research purposes.
translated by 谷歌翻译