布料的机器人操作的应用包括织物制造业到处理毯子和洗衣。布料操作对于机器人而言是挑战，这主要是由于它们的高度自由度，复杂的动力学和折叠或皱巴巴配置时的严重自我闭合。机器人操作的先前工作主要依赖于视觉传感器，这可能会对细粒度的操纵任务构成挑战，例如从一堆布上抓住所需数量的布料层。在本文中，我们建议将触觉传感用于布操作；我们将触觉传感器（Resin）连接到弗兰卡机器人的两个指尖之一，并训练分类器，以确定机器人是否正在抓住特定数量的布料层。在测试时间实验中，机器人使用此分类器作为其政策的一部分，使用触觉反馈来掌握一两个布层，以确定合适的握把。实验结果超过180次物理试验表明，与使用图像分类器的方法相比，所提出的方法优于不使用触觉反馈并具有更好地看不见布的基准。代码，数据和视频可在https://sites.google.com/view/reskin-cloth上找到。

Privacy noise may negate the benefits of using adaptive optimizers in differentially private model training. Prior works typically address this issue by using auxiliary information (e.g., public data) to boost the effectiveness of adaptive optimization. In this work, we explore techniques to estimate and efficiently adapt to gradient geometry in private adaptive optimization without auxiliary data. Motivated by the observation that adaptive methods can tolerate stale preconditioners, we propose differentially private adaptive training with delayed preconditioners (DP^2), a simple method that constructs delayed but less noisy preconditioners to better realize the benefits of adaptivity. Theoretically, we provide convergence guarantees for our method for both convex and non-convex problems, and analyze trade-offs between delay and privacy noise reduction. Empirically, we explore DP^2 across several real-world datasets, demonstrating that it can improve convergence speed by as much as 4x relative to non-adaptive baselines and match the performance of state-of-the-art optimization methods that require auxiliary data.

Household environments are visually diverse. Embodied agents performing Vision-and-Language Navigation (VLN) in the wild must be able to handle this diversity, while also following arbitrary language instructions. Recently, Vision-Language models like CLIP have shown great performance on the task of zero-shot object recognition. In this work, we ask if these models are also capable of zero-shot language grounding. In particular, we utilize CLIP to tackle the novel problem of zero-shot VLN using natural language referring expressions that describe target objects, in contrast to past work that used simple language templates describing object classes. We examine CLIP's capability in making sequential navigational decisions without any dataset-specific finetuning, and study how it influences the path that an agent takes. Our results on the coarse-grained instruction following task of REVERIE demonstrate the navigational capability of CLIP, surpassing the supervised baseline in terms of both success rate (SR) and success weighted by path length (SPL). More importantly, we quantitatively show that our CLIP-based zero-shot approach generalizes better to show consistent performance across environments when compared to SOTA, fully supervised learning approaches when evaluated via Relative Change in Success (RCS).

The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common approaches, but current methods have considerable limitations.For example, fine-tuning an existing policy frequently fails, as the policy can degrade rapidly early in training. In a similar vein, distillation of expert behavior can lead to poor results when given sub-optimal experts. We compare several common approaches for skill transfer on multiple domains including changes in task and system dynamics. We identify how existing methods can fail and introduce an alternative approach to mitigate these problems. Our approach learns to sequence existing temporally-extended skills for exploration but learns the final policy directly from the raw experience. This conceptual split enables rapid adaptation and thus efficient data collection but without constraining the final solution.It significantly outperforms many classical methods across a suite of evaluation tasks and we use a broad set of ablations to highlight the importance of differentc omponents of our method.

Despite their popularity in deep learning and machine learning in general, the theoretical properties of adaptive optimizers such as Adagrad, RMSProp, Adam or AdamW are not yet fully understood. In this paper, we develop a novel framework to study the stability and generalization of these optimization methods. Based on this framework, we show provable guarantees about such properties that depend heavily on a single parameter $\beta_2$. Our empirical experiments support our claims and provide practical insights into the stability and generalization properties of adaptive optimization methods.

从过去的经验中发现有用的行为并将其转移到新任务的能力被认为是自然体现智力的核心组成部分。受神经科学的启发，发现在瓶颈状态下切换的行为一直被人们追求，以引起整个任务的最小描述长度的计划。先前的方法仅支持在线，政策，瓶颈状态发现，限制样本效率或离散的状态行动域，从而限制适用性。为了解决这个问题，我们介绍了基于模型的离线选项（MO2），这是一个脱机后视框架，支持在连续的状态行动空间上发现样品效率高效瓶颈选项。一旦脱机而在源域上学习了瓶颈选项，它们就会在线转移，以改善转移域的探索和价值估计。我们的实验表明，在复杂的长途连续控制任务上，具有稀疏，延迟的奖励，MO2的属性至关重要，并且导致性能超过最近的选项学习方法。其他消融进一步证明了对期权可预测性和信用分配的影响。

权重规范$ \ | w \ | $和保证金$ \ gamma $通过归一化的保证金$ \ gamma/\ | w \ | $参与学习理论。由于标准神经净优化器不能控制归一化的边缘，因此很难测试该数量是否与概括有关。本文设计了一系列实验研究，这些研究明确控制了归一化的边缘，从而解决了两个核心问题。首先：归一化的边缘是否总是对概括产生因果影响？本文发现，在归一化的边缘似乎与概括没有关系的情况下，可以与Bartlett等人的理论背道而驰。（2017）。第二：标准化边缘是否对概括有因果影响？该论文发现是的 - 在标准培训设置中，测试性能紧密跟踪了标准化的边距。该论文将高斯流程模型表示为这种行为的有前途的解释。

自适应优化方法已成为许多机器学习任务的默认求解器。不幸的是，适应性的好处可能会在具有不同隐私的训练时降低，因为噪声增加了，以确保隐私会降低自适应预处理的有效性。为此，我们提出了ADADP，这是一个使用非敏感的侧面信息来预处梯度的一般框架，从而可以在私有设置中有效使用自适应方法。我们正式显示ADADPS减少了获得类似隐私保证所需的噪声量，从而提高了优化性能。从经验上讲，我们利用简单且随时可用的侧面信息来探索实践中ADADP的性能，与集中式和联合设置中的强大基线相比。我们的结果表明，ADADP平均提高了准确性7.7％（绝对） - 在大规模文本和图像基准上产生最先进的隐私性权衡权衡。

与SGD相比，Adam等自适应梯度方法允许对现代深层网络（尤其是大型语言模型）进行强有力的培训。但是，适应性的使用不仅是为了额外的记忆，而且还提出了一个基本问题：SGD等非自适应方法可以享受类似的好处吗？在本文中，我们通过提议通过以下一般配方提议实现健壮和记忆效率的培训来为这个问题提供肯定的答案：（1）修改体系结构并使IT规模不变，即参数规模不影响。网络的输出，（2）使用SGD和重量衰减的训练，以及（3）剪辑全局梯度标准与重量标准成比例成正比，乘以$ \ sqrt {\ tfrac {\ tfrac {2 \ lambda} {\ eta}} {\ eta}}} $， $ \ eta $是学习率，而$ \ lambda $是权重腐烂。我们表明，这种一般方法是通过证明其收敛性仅取决于初始化和损失的规模来重新恢复参数和丢失的强大，而标准SGD甚至可能不会收敛许多初始化。在我们的食谱之后，我们设计了一个名为Sibert的Bert版本的比例不变版本，该版本仅由Vanilla SGD进行训练时，可以实现与Bert在下游任务中受过自适应方法训练的BERT相当的性能。

对于在现实世界中运营的机器人来说，期望学习可以有效地转移和适应许多任务和场景的可重复使用的行为。我们提出了一种使用分层混合潜变量模型来从数据中学习抽象运动技能的方法。与现有工作相比，我们的方法利用了离散和连续潜在变量的三级层次结构，以捕获一组高级行为，同时允许如何执行它们的差异。我们在操纵域中展示该方法可以有效地将离线数据脱落到不同的可执行行为，同时保留连续潜变量模型的灵活性。由此产生的技能可以在新的任务，看不见的对象和州内转移和微调到基于视觉的策略，与现有的技能和仿制的方法相比，产生更好的样本效率和渐近性能。我们进一步分析了技能最有益的方式以及何时：他们鼓励定向探索来涵盖与任务相关的国家空间的大区域，使其在挑战稀疏奖励环境中最有效。